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

    Neuronpedia

    INDEX
    Explanations

    commands and processes

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    velle
    0.71
    បន្ទ
    0.66
    ችን
    0.65
    ziale
    0.64
    したら
    0.64
    Луч
    0.64
    వరి
    0.63
    धारणा
    0.63
     overrated
    0.63
    വിത
    0.63
    POSITIVE LOGITS
     way
    0.77
     ICP
    0.75
    SFR
    0.72
     SFR
    0.71
     k
    0.70
     Kron
    0.70
     STORM
    0.70
    ṛ
    0.69
     DC
    0.69
     Q
    0.69
    Act Density 0.000%

    No Known Activations