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

    Neuronpedia

    INDEX
    Explanations

    see

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ele
    -0.07
     entityType
    -0.07
    _direction
    -0.07
    _member
    -0.07
    _identifier
    -0.07
    .pg
    -0.06
    _ment
    -0.06
    _micro
    -0.06
     gdk
    -0.06
    .undo
    -0.06
    POSITIVE LOGITS
    sent
    0.07
    inta
    0.06
    افة
    0.06
    らない
    0.06
    дать
    0.06
    recipe
    0.06
     concealed
    0.06
     contingency
    0.06
    ätze
    0.06
     Passage
    0.06
    Act Density 0.107%

    No Known Activations