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

    Neuronpedia

    INDEX
    Explanations

    have

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    severity
    -0.07
    entai
    -0.07
    ought
    -0.07
    (fill
    -0.07
    価
    -0.06
    kę
    -0.06
     Run
    -0.06
    into
    -0.06
    identify
    -0.06
     knocked
    -0.06
    POSITIVE LOGITS
    ा।↵↵
    0.07
    uebas
    0.07
     Beautiful
    0.06
    .*/↵
    0.06
    ازند
    0.06
     ----------------------------------------------------------------------------
    0.06
    尋
    0.06
     генера
    0.06
    pal
    0.06
    Jonathan
    0.06
    Act Density 0.001%

    No Known Activations