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

    Neuronpedia

    INDEX
    Explanations

    signals and their meaning

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ari
    0.93
    kins
    0.92
    :
    0.89
    ning
    0.88
    k
    0.85
    ography
    0.84
     in
    0.84
    ya
    0.83
    𝐬
    0.80
     uninformed
    0.79
    POSITIVE LOGITS
    Signals
    1.13
    де
    1.10
     signals
    1.09
    信号
    1.09
     Signals
    1.09
    Signal
    1.06
     señales
    1.04
    드릴
    1.03
     sinais
    1.02
    K
    1.00
    Act Density 0.015%

    No Known Activations