Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    terms related to permissions and rights, particularly in a software or legal context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    Code-related words and licenses

    np_acts-logits-general · gemini-2.0-flash

    use "Software" or "defense"

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ↵
    -0.72
    </b>
    -0.71
     everybody
    -0.63
      
    -0.60
    </strong>
    -0.60
     stuff
    -0.59
    ！
    -0.59
    }/>
    -0.58
    }
    -0.57
     jScrollPane
    -0.57
    POSITIVE LOGITS
     muualla
    0.68
    DockStyle
    0.67
    IRQn
    0.62
     Alamy
    0.61
    Ārējās
    0.61
     relâche
    0.60
     esternos
    0.60
     varandra
    0.58
     vänner
    0.57
    .*")]
    0.56
    Act Density 0.001%

    No Known Activations