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

    Neuronpedia

    INDEX
    Explanations

    false context, predictive AI

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ',
    0.51
    0.48
    ,'
    0.48
    zo
    0.47
    (?:
    0.44
    jø
    0.43
    er
    0.43
    ii
    0.42
    ')
    0.40
    ':'
    0.40
    POSITIVE LOGITS
    णाऱ्या
    0.44
    रोक
    0.44
    CallOptions
    0.43
    Cause
    0.42
     мобиль
    0.42
    녈
    0.42
     вероят
    0.42
     سونے
    0.41
    츨
    0.41
    Carbon
    0.41
    Act Density 0.001%

    No Known Activations