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

    Neuronpedia

    INDEX
    Explanations

    after

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     FD
    -0.08
    studio
    -0.07
     QLD
    -0.07
     Jer
    -0.07
    .Health
    -0.07
     Yönetim
    -0.07
     bulb
    -0.07
     wondered
    -0.07
     Darren
    -0.07
    warehouse
    -0.06
    POSITIVE LOGITS
     avoid
    0.08
    祲
    0.07
    terms
    0.07
    適用
    0.07
    .Atomic
    0.07
     rout
    0.07
    亲属
    0.07
    .flatten
    0.06
    .BOLD
    0.06
    눙
    0.06
    Act Density 0.084%

    No Known Activations