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

    Neuronpedia

    INDEX
    Explanations

    iments

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     receives
    -0.07
     remembered
    -0.06
    Hierarchy
    -0.06
     noci
    -0.06
     pulse
    -0.06
    羽
    -0.06
     Palo
    -0.06
     Raider
    -0.06
     steam
    -0.06
     pierced
    -0.06
    POSITIVE LOGITS
    0.07
    =forms
    0.07
    clone
    0.06
    zerbai
    0.06
          
↵
    0.06
    format
    0.06
     наб
    0.06
           
↵
    0.06
    _fmt
    0.06
    0.06
    Act Density 0.001%

    No Known Activations