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

    Neuronpedia

    INDEX
    Explanations

    crisis support text line

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Turning
    0.78
     Turning
    0.78
     strutt
    0.76
     turned
    0.73
     Ref
    0.71
     turning
    0.70
    turning
    0.69
     STRUCTURE
    0.68
     Update
    0.68
    turned
    0.67
    POSITIVE LOGITS
    oyne
    0.74
    NaOMe
    0.72
    ገር
    0.69
    aguchi
    0.68
    isSignedIn
    0.67
    ]=="
    0.66
    agle
    0.66
    ocamp
    0.65
    createElement
    0.64
    istan
    0.64
    Act Density 0.002%

    No Known Activations