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

    Neuronpedia

    INDEX
    Explanations

    slider

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     summarize
    -0.06
     安
    -0.06
    _grp
    -0.06
    .pref
    -0.06
    crease
    -0.06
     Cumberland
    -0.06
     XI
    -0.06
     tutte
    -0.06
    /met
    -0.06
     топ
    -0.06
    POSITIVE LOGITS
    िन
    0.07
     addr
    0.07
     horrend
    0.06
    ([('
    0.06
     seasoned
    0.06
    urm
    0.06
    conscious
    0.06
    fork
    0.06
    _outline
    0.06
    �
    0.06
    Act Density 0.004%

    No Known Activations