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

    Neuronpedia

    INDEX
    Explanations

    org

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Fac
    -0.06
     Fay
    -0.06
     реє
    -0.06
    adastro
    -0.06
     incidence
    -0.06
    ви
    -0.06
     wellbeing
    -0.06
    ileri
    -0.06
    /values
    -0.06
     ((*
    -0.06
    POSITIVE LOGITS
    heels
    0.08
    .finished
    0.07
    pictured
    0.07
    _deps
    0.06
     труб
    0.06
     mest
    0.06
     educating
    0.06
     mango
    0.06
     ili
    0.06
    Amb
    0.06
    Act Density 0.007%

    No Known Activations