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

    Neuronpedia

    INDEX
    Explanations

    action verbs describing processes

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     longstanding
    1.24
     sensational
    1.19
     thei
    1.15
     bureaucratic
    1.14
     strikingly
    1.13
     tinkering
    1.12
     suburban
    1.12
     wildly
    1.12
     legitimate
    1.11
     flashy
    1.10
    POSITIVE LOGITS
    H
    0.80
    IC
    0.79
    Y
    0.73
    O
    0.73
    E
    0.72
    I
    0.70
    C
    0.69
    P
    0.68
    F
    0.68
    Ac
    0.67
    Act Density 0.138%

    No Known Activations