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

    Neuronpedia

    INDEX
    Explanations

    social needs and services

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    e
    1.17
    ma
    1.07
    o
    1.06
    p
    0.99
    ে
    0.98
    eing
    0.95
    a
    0.92
    cem
    0.92
    en
    0.90
    passwd
    0.89
    POSITIVE LOGITS
    istic
    0.92
     necessities
    0.87
     dźwię
    0.87
    ////////////////
    0.86
     correlated
    0.86
     withd
    0.86
     efficacy
    0.86
     tribulations
    0.85
     exemptions
    0.84
    铑
    0.83
    Act Density 0.373%

    No Known Activations