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

    Neuronpedia

    INDEX
    Explanations

    Comma

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     힘
    -0.07
    swana
    -0.07
     oby
    -0.07
    actice
    -0.07
     reaching
    -0.07
     Eig
    -0.07
    森
    -0.07
     sollte
    -0.06
    editar
    -0.06
    翼
    -0.06
    POSITIVE LOGITS
     thereby
    0.07
    mits
    0.07
    .cross
    0.06
    instant
    0.06
    .intersection
    0.06
     allocating
    0.06
    _dims
    0.06
    ographical
    0.06
    depart
    0.06
     Msg
    0.06
    Act Density 0.001%

    No Known Activations