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

    Neuronpedia

    INDEX
    Explanations

    Code examples/snippets

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    גלי
    -0.07
    战斗
    -0.07
    밥
    -0.07
    zes
    -0.07
    Mesh
    -0.07
    깨
    -0.06
     Leaf
    -0.06
    ctl
    -0.06
    ushed
    -0.06
    들과
    -0.06
    POSITIVE LOGITS
     Islanders
    0.07
    ).(
    0.07
    ISyntaxException
    0.07
     EG
    0.06
     responders
    0.06
    �
    0.06
     aproxim
    0.06
     predomin
    0.06
    ']=$
    0.06
     thor
    0.06
    Act Density 0.186%

    No Known Activations