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

    Neuronpedia

    INDEX
    Explanations

    *

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Defense
    -0.08
    apk
    -0.07
     UIWindow
    -0.07
    levator
    -0.07
     어느
    -0.07
     отдых
    -0.06
    ,event
    -0.06
     pager
    -0.06
     relay
    -0.06
     babys
    -0.06
    POSITIVE LOGITS
    强壮
    0.08
    -high
    0.07
    NullOrEmpty
    0.07
    (',')[
    0.07
     enough
    0.07
    很高
    0.07
    気�
    0.07
    monic
    0.07
    水利工程
    0.06
    禔
    0.06
    Act Density 0.000%

    No Known Activations