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

    Neuronpedia

    INDEX
    Explanations

    expressing alternatives/contrasts

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     verbose
    -0.07
    ramento
    -0.06
     усіх
    -0.06
     Diagram
    -0.06
     �
    -0.06
     log
    -0.06
    wards
    -0.06
    �
    -0.06
    ولوج
    -0.06
    ++){↵↵
    -0.06
    POSITIVE LOGITS
    必要
    0.08
    اعات
    0.07
     POLL
    0.06
    思
    0.06
    _BYTE
    0.06
     разом
    0.06
    .semantic
    0.06
    텔
    0.06
     '^
    0.06
    //:
    0.06
    Act Density 0.001%

    No Known Activations