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

    Neuronpedia

    INDEX
    Explanations

    fw

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Advance
    -0.07
     siz
    -0.07
    또
    -0.06
     ont
    -0.06
    Li
    -0.06
    �
    -0.06
     articulated
    -0.06
    ็น
    -0.06
     дж
    -0.06
     SOCIAL
    -0.06
    POSITIVE LOGITS
     implications
    0.07
    ograd
    0.07
     maybe
    0.07
    Updating
    0.06
     certainly
    0.06
     Theft
    0.06
    declaring
    0.06
    filter
    0.06
    ável
    0.06
    ximity
    0.06
    Act Density 0.003%

    No Known Activations