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

    Neuronpedia

    INDEX
    Explanations

    code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    cap
    -0.07
     Lau
    -0.07
     humane
    -0.06
     Investigators
    -0.06
     Şampiyon
    -0.06
     Putin
    -0.06
    _secs
    -0.06
     bf
    -0.06
     disappearance
    -0.06
     Rotation
    -0.06
    POSITIVE LOGITS
    ENTS
    0.07
    pping
    0.07
     handle
    0.07
    ाड
    0.07
    sel
    0.06
     spirits
    0.06
    VO
    0.06
    Inicial
    0.06
    าท
    0.06
    จะ
    0.06
    Act Density 0.000%

    No Known Activations