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

    Neuronpedia

    INDEX
    Explanations

    0

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     ejected
    -0.07
     slammed
    -0.07
    FINE
    -0.07
    ウ
    -0.06
     добав
    -0.06
     Osc
    -0.06
     maize
    -0.06
    aq
    -0.06
     Red
    -0.06
    .;.;.;.;
    -0.06
    POSITIVE LOGITS
     logistical
    0.07
     дос
    0.07
    _heads
    0.07
    .disc
    0.06
    works
    0.06
    _fix
    0.06
    .dx
    0.06
    Adv
    0.06
    หล
    0.06
    日期
    0.06
    Act Density 0.006%

    No Known Activations