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

    Neuronpedia

    INDEX
    Explanations

    references to the speaker and expressions of personal experiences

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

    First-person perspective

    np_acts-logits-general · gemini-2.0-flash

    I, we, you

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    
    -0.54
     ولد
    -0.50
    AccessorTable
    -0.49
     مما
    -0.43
    glLoadIdentity
    -0.43
    页
    -0.41
     err
    -0.41
    Doing
    -0.41
    XPATH
    -0.40
    .*")]
    -0.40
    POSITIVE LOGITS
     dearly
    0.68
     sorely
    0.64
     deem
    0.63
     deems
    0.63
     otherwise
    0.63
    ureusement
    0.62
     zuvor
    0.61
    hopefully
    0.60
    +#+#
    0.59
     betweenstory
    0.59
    Act Density 0.280%

    No Known Activations