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

    Neuronpedia

    INDEX
    Explanations

    violence

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Transformation
    -0.08
     слыш
    -0.07
    mailto
    -0.06
    ographed
    -0.06
    -Owned
    -0.06
    ologie
    -0.06
    scaling
    -0.06
    urope
    -0.06
    EFAULT
    -0.06
     уточ
    -0.06
    POSITIVE LOGITS
    رود
    0.06
    <Category
    0.06
     �
    0.06
     Res
    0.06
    avior
    0.06
    _ls
    0.06
    ]:=
    0.06
    .Real
    0.06
    대표
    0.06
    .Lines
    0.05
    Act Density 0.032%

    No Known Activations