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

    Neuronpedia

    INDEX
    Explanations

    Instructions, proposals

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Kend
    -0.07
    (java
    -0.07
     rẻ
    -0.07
    uno
    -0.07
     pohy
    -0.06
     Typeface
    -0.06
     Stamina
    -0.06
    Tickets
    -0.06
     fotograf
    -0.06
    ETO
    -0.06
    POSITIVE LOGITS
    _loaded
    0.07
    -Z
    0.06
     하고
    0.06
     mapper
    0.06
     ді
    0.06
     слов
    0.06
    pop
    0.06
    angled
    0.06
    rolls
    0.06
    ウ
    0.06
    Act Density 0.048%

    No Known Activations