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

    Neuronpedia

    INDEX
    Explanations

    and

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    -comp
    -0.06
    around
    -0.06
    .Cryptography
    -0.06
    _sp
    -0.06
    included
    -0.06
     supremacist
    -0.06
     رود
    -0.06
    сион
    -0.06
     освіти
    -0.06
    _Items
    -0.06
    POSITIVE LOGITS
    ações
    0.07
    permissions
    0.07
     atoi
    0.07
     welche
    0.06
    *h
    0.06
    çois
    0.06
     aerospace
    0.06
    iele
    0.06
    umbs
    0.06
    ledge
    0.06
    Act Density 0.106%

    No Known Activations