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

    Neuronpedia

    INDEX
    Explanations

    impact

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     تزيد
    -0.08
     sumar
    -0.08
     الغاز
    -0.08
     triệu
    -0.08
    天空
    -0.07
     summed
    -0.07
     jez
    -0.07
    \Schema
    -0.07
     zicht
    -0.07
     rinn
    -0.07
    POSITIVE LOGITS
     fragile
    0.11
     frag
    0.10
     delicate
    0.10
     повреж
    0.10
    事故
    0.10
    损
    0.09
     vibrations
    0.09
     Frag
    0.09
    Sensitive
    0.09
     precautions
    0.09
    Act Density 0.032%

    No Known Activations