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

    Neuronpedia

    INDEX
    Explanations

    family members or units

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    BAND
    0.86
    Plas
    0.86
    IR
    0.85
    Dar
    0.83
    Band
    0.82
    Badge
    0.81
    Aspect
    0.80
    Play
    0.80
    Dial
    0.80
    Call
    0.78
    POSITIVE LOGITS
     dete
    0.93
     rearview
    0.89
     dapp
    0.86
    ıya
    0.86
    кты
    0.85
     pessimistic
    0.84
     seco
    0.84
     inlet
    0.83
     HMO
    0.83
    ାନ
    0.82
    Act Density 0.001%

    No Known Activations