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

    Neuronpedia

    INDEX
    Explanations

    but

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    glm
    -0.07
     通
    -0.07
     Wanted
    -0.07
     elig
    -0.07
     predic
    -0.06
    äs
    -0.06
     belirli
    -0.06
     benöt
    -0.06
    Ja
    -0.06
    сот
    -0.06
    POSITIVE LOGITS
    serialize
    0.08
    HUD
    0.06
    COPY
    0.06
    .=
    0.06
     Follow
    0.06
     invaluable
    0.06
    etros
    0.06
    419
    0.06
    νή
    0.06
    998
    0.06
    Act Density 0.010%

    No Known Activations