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

    Neuronpedia

    INDEX
    Explanations

    code initialization

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    cision
    0.89
    is
    0.79
    step
    0.76
    element
    0.75
    5
    0.74
    high
    0.72
    8
    0.69
    ylis
    0.69
     dari
    0.68
    china
    0.68
    POSITIVE LOGITS
    抟
    0.80
     Comenz
    0.74
    TLE
    0.68
    IONS
    0.68
     Freshman
    0.68
    Fiscal
    0.67
    栻
    0.67
     Fourteenth
    0.66
    დესაც
    0.66
     賞
    0.66
    Act Density 0.021%

    No Known Activations