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

    Neuronpedia

    INDEX
    Explanations

    view

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ा
    -0.07
    Cancel
    -0.07
     ling
    -0.06
    ул
    -0.06
    {o
    -0.06
    _arm
    -0.06
     대
    -0.06
    KM
    -0.06
    11
    -0.06
     (-
    -0.06
    POSITIVE LOGITS
    agree
    0.07
     �
    0.07
     желез
    0.06
     Blair
    0.06
    PB
    0.06
     alumnos
    0.06
    غان
    0.06
    ritable
    0.06
    ereum
    0.06
     cath
    0.06
    Act Density 0.005%

    No Known Activations