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

    Neuronpedia

    INDEX
    Explanations

    Palestinian

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    -array
    -0.07
    Mon
    -0.07
    fluid
    -0.07
    (customer
    -0.07
    _BUSY
    -0.07
    _accum
    -0.07
    ortion
    -0.07
    COME
    -0.07
    _present
    -0.06
    蕈
    -0.06
    POSITIVE LOGITS
    啥
    0.07
     그러나
    0.07
    ');
↵
    0.07
    '";
↵
    0.07
     somewhat
    0.07
     vote
    0.07
     есть
    0.07
     terrible
    0.07
     tai
    0.07
    ₪
    0.06
    Act Density 0.005%

    No Known Activations