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

    Neuronpedia

    INDEX
    Explanations

    data

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    (strategy
    -0.07
    เขต
    -0.07
     ký
    -0.07
    _phase
    -0.07
    ERAL
    -0.07
     Excellent
    -0.07
     dissolved
    -0.07
    thead
    -0.07
    Voltage
    -0.06
    Snackbar
    -0.06
    POSITIVE LOGITS
     вок
    0.06
    电脑
    0.06
    (Temp
    0.06
     Aeros
    0.06
     Pascal
    0.06
     sản
    0.06
    =".$_
    0.06
    ientras
    0.06
     сир
    0.06
    simp
    0.05
    Act Density 0.034%

    No Known Activations