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

    Neuronpedia

    INDEX
    Explanations

    the

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    (Project
    -0.07
     Sc
    -0.07
     Arbeit
    -0.07
     Battles
    -0.07
    izontal
    -0.06
    ρχ
    -0.06
    spent
    -0.06
    季
    -0.06
     Raid
    -0.06
    cms
    -0.06
    POSITIVE LOGITS
     cpf
    0.07
    .',
    0.07
    .GetText
    0.06
    ­ing
    0.06
     NA
    0.06
    xEB
    0.06
    孩子
    0.06
     aj
    0.06
    、どう
    0.06
    -multi
    0.06
    Act Density 0.029%

    No Known Activations