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

    Neuronpedia

    INDEX
    Explanations

    129

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    acl
    -0.07
    (xy
    -0.07
     scept
    -0.07
     Decom
    -0.07
    /am
    -0.07
    dě
    -0.07
    يري
    -0.07
     plaint
    -0.07
    iał
    -0.07
     Jugend
    -0.07
    POSITIVE LOGITS
    129
    0.08
     почти
    0.06
     erotisch
    0.06
    :string
    0.06
     respective
    0.06
    REQUIRED
    0.06
     Automatically
    0.06
     yrs
    0.06
     advise
    0.06
     ACCEPT
    0.06
    Act Density 0.000%

    No Known Activations