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

    Neuronpedia

    INDEX
    Explanations

    ous

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     longer
    -0.06
    兄
    -0.06
    乾
    -0.06
     دشمن
    -0.06
    -can
    -0.06
     давно
    -0.06
     Writes
    -0.06
    -label
    -0.06
    TM
    -0.06
     backbone
    -0.06
    POSITIVE LOGITS
    ous
    0.07
     μο
    0.07
    ::*;↵↵
    0.07
     pattern
    0.07
    azes
    0.07
     Marijuana
    0.07
    atos
    0.07
    áticas
    0.07
    names
    0.06
    ато
    0.06
    Act Density 0.001%

    No Known Activations