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

    Neuronpedia

    INDEX
    Explanations

    google links and resources

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Phi
    0.40
    Locked
    0.40
    locked
    0.38
    oblasts
    0.38
    相位
    0.38
     restrict
    0.37
     Nef
    0.36
     Pha
    0.36
    restrict
    0.35
    Approx
    0.35
    POSITIVE LOGITS
     evade
    0.44
    jería
    0.43
     Ew
    0.42
    inje
    0.41
     Temporal
    0.40
     temporal
    0.39
    istern
    0.39
     gt
    0.37
     tonel
    0.37
     EntityManager
    0.37
    Act Density 0.005%

    No Known Activations