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

    Neuronpedia

    INDEX
    Explanations

    btn and alert

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    $)$.
    0.42
    خیص
    0.42
    嶌
    0.41
     vulve
    0.39
    इनस
    0.39
    positroid
    0.39
    nosti
    0.38
    avanje
    0.38
    hydes
    0.38
     magnetometer
    0.38
    POSITIVE LOGITS
    <0xE3>
    0.44
    -
    0.41
    <0xE2>
    0.40
    ๆ
    0.40
    々は
    0.36
     பட்ட
    0.36
    _
    0.36
    ↵
    0.36
       
    0.35
    et
    0.35
    Act Density 0.004%

    No Known Activations