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

    Neuronpedia

    INDEX
    Explanations

    for

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .Transform
    -0.07
    backs
    -0.06
     Mons
    -0.06
    kom
    -0.06
     клас
    -0.06
    stein
    -0.06
     seaside
    -0.06
     smiling
    -0.06
     derivatives
    -0.06
    :M
    -0.06
    POSITIVE LOGITS
    rowth
    0.07
    amacare
    0.07
    Na
    0.07
    _One
    0.06
    ahrungen
    0.06
    Scientists
    0.06
     dgv
    0.06
    spar
    0.06
    offee
    0.06
    okt
    0.06
    Act Density 0.222%

    No Known Activations