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

    Neuronpedia

    INDEX
    Explanations

    increases and diminishes

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     fluctuates
    0.49
     rotates
    0.48
     mike
    0.47
     inizia
    0.46
     bút
    0.46
     inizio
    0.44
     iniziamo
    0.44
     mozz
    0.42
     unfolding
    0.42
    转变
    0.42
    POSITIVE LOGITS
    ouver
    0.43
    McC
    0.42
    linearity
    0.41
    Severity
    0.41
    xas
    0.40
     McC
    0.40
    ặp
    0.40
    severity
    0.39
    specificity
    0.39
    Establish
    0.39
    Act Density 0.044%

    No Known Activations