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

    Neuronpedia

    INDEX
    Explanations

    why

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     батар
    -0.07
     Clarkson
    -0.07
     расстоя
    -0.07
    poz
    -0.06
     技
    -0.06
     towards
    -0.06
    "$
    -0.06
    Usuarios
    -0.06
     dolaş
    -0.06
    ucch
    -0.06
    POSITIVE LOGITS
    _mk
    0.08
    Wide
    0.07
    value
    0.07
     ham
    0.07
    イツ
    0.06
    AuthToken
    0.06
     Riverside
    0.06
    ernal
    0.06
    HOLDER
    0.06
    	double
    0.06
    Act Density 0.026%

    No Known Activations