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

    Neuronpedia

    INDEX
    Explanations

    /

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    -node
    -0.07
     opak
    -0.06
    .UP
    -0.06
     folders
    -0.06
     conservatism
    -0.06
     folder
    -0.06
    出去
    -0.06
    -turned
    -0.06
    ufe
    -0.06
    (System
    -0.06
    POSITIVE LOGITS
     cannabinoids
    0.08
     attravers
    0.07
    pto
    0.07
    arch
    0.06
     گرم
    0.06
     проведения
    0.06
    lı
    0.06
     saturn
    0.06
    iji
    0.06
     defeats
    0.06
    Act Density 0.008%

    No Known Activations