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

    Neuronpedia

    INDEX
    Explanations

    the

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     haunting
    -0.07
    .extern
    -0.07
    ,strong
    -0.06
    —in
    -0.06
    _SCENE
    -0.06
     эп
    -0.06
    出的
    -0.06
     �
    -0.06
     Mothers
    -0.06
    ิตร
    -0.06
    POSITIVE LOGITS
     brasile
    0.07
    _tickets
    0.06
    average
    0.06
     factories
    0.06
     شکست
    0.06
     негатив
    0.06
     crews
    0.06
    ektedir
    0.06
     exported
    0.06
     shifting
    0.06
    Act Density 0.035%

    No Known Activations