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

    Neuronpedia

    INDEX
    Explanations

    examples, cases

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Crowd
    -0.07
     Law
    -0.06
     möchte
    -0.06
     trebuie
    -0.06
    ToDo
    -0.06
     당
    -0.06
     boat
    -0.06
    EndPoint
    -0.06
    钢
    -0.06
    -esteem
    -0.06
    POSITIVE LOGITS
     manifestations
    0.06
     tổn
    0.06
     jLabel
    0.06
    _ERRORS
    0.06
     producción
    0.06
    _pipeline
    0.06
     overturn
    0.06
     instantiated
    0.06
    (".
    0.06
     {\↵
    0.06
    Act Density 0.036%

    No Known Activations