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

    Neuronpedia

    INDEX
    Explanations

    attacks, false flags

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Auth
    -0.07
    JSON
    -0.06
     Job
    -0.06
    Collision
    -0.06
    489
    -0.06
    Buscar
    -0.06
    Checker
    -0.06
     provincial
    -0.06
    (r
    -0.06
    ahl
    -0.06
    POSITIVE LOGITS
     MEM
    0.08
     filmes
    0.07
    (groups
    0.07
    pel
    0.06
    cached
    0.06
    ваем
    0.06
     schöne
    0.06
     Unc
    0.06
     scrutin
    0.06
    ={[
    0.06
    Act Density 0.017%

    No Known Activations