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

    Neuronpedia

    INDEX
    Explanations

    nav

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ===========↵
    -0.08
     further
    -0.07
    老爷
    -0.07
    公立医院
    -0.06
     sog
    -0.06
    -0.06
    ❐
    -0.06
    odos
    -0.06
    쨈
    -0.06
     barr
    -0.06
    POSITIVE LOGITS
    Convertible
    0.08
    に行く
    0.07
    —I
    0.07
     Minimum
    0.07
     UI
    0.07
    越高
    0.06
    異なる
    0.06
    �
    0.06
    DivElement
    0.06
    剪
    0.06
    Act Density 0.001%

    No Known Activations