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

    Neuronpedia

    INDEX
    Explanations

    first

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     reconcile
    -0.08
    uala
    -0.07
    .setFill
    -0.07
     %%↵
    -0.07
     beautiful
    -0.07
     escol
    -0.07
     lleg
    -0.07
    高清
    -0.07
    earable
    -0.06
     indul
    -0.06
    POSITIVE LOGITS
    (paren
    0.07
    _PHOTO
    0.06
    WO
    0.06
     Eh
    0.06
    FK
    0.06
    묾
    0.06
    Documents
    0.06
    vented
    0.06
    RT
    0.06
    是我
    0.06
    Act Density 0.008%

    No Known Activations