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

    Neuronpedia

    INDEX
    Explanations

    conversational snippets

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Living
    -0.07
    <W
    -0.07
     využití
    -0.06
    ported
    -0.06
    EqualTo
    -0.06
    shows
    -0.06
     VIA
    -0.06
     expanding
    -0.06
     душ
    -0.06
     initiator
    -0.06
    POSITIVE LOGITS
    .LatLng
    0.06
    Effect
    0.06
    痛
    0.06
    AMILY
    0.06
     **/↵↵
    0.06
     gunfire
    0.06
    egas
    0.06
     =========================================================================
    0.06
    ęp
    0.06
     fuck
    0.06
    Act Density 0.033%

    No Known Activations