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

    Neuronpedia

    INDEX
    Explanations

    in

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .-
    -0.08
    /mm
    -0.07
     apprentice
    -0.07
     crus
    -0.07
     addicted
    -0.06
     вин
    -0.06
     trucks
    -0.06
     definitions
    -0.06
    _folders
    -0.06
     uniforms
    -0.06
    POSITIVE LOGITS
    ál
    0.07
     Dup
    0.07
     RTL
    0.06
    рать
    0.06
    [{
    0.06
    AH
    0.06
     mang
    0.06
    σουν
    0.06
     факти
    0.06
     Anglic
    0.06
    Act Density 0.000%

    No Known Activations