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

    Neuronpedia

    INDEX
    Explanations

    Effect

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    iversary
    -0.06
    طبيق
    -0.06
    _rad
    -0.06
    λης
    -0.06
    드
    -0.06
    ге
    -0.06
    _mi
    -0.06
     каждый
    -0.06
    ائلة
    -0.06
    (:
    -0.06
    POSITIVE LOGITS
    Effects
    0.07
     Ribbon
    0.07
     Decom
    0.06
     Templates
    0.06
     Effect
    0.06
    ,’”
    0.06
     Lisp
    0.06
     söylem
    0.06
    ’.
    0.06
     consum
    0.06
    Act Density 0.005%

    No Known Activations