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

    Neuronpedia

    INDEX
    Explanations

    scientific research

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    書
    -0.07
     tortured
    -0.07
    .Round
    -0.07
     �
    -0.07
    .defaults
    -0.06
    .Shapes
    -0.06
     національ
    -0.06
     isp
    -0.06
    Ray
    -0.06
    Ask
    -0.06
    POSITIVE LOGITS
    openhagen
    0.07
     ظ
    0.06
    operands
    0.06
    Công
    0.06
     Zeit
    0.06
    rası
    0.06
    0.06
     gelişim
    0.06
    mente
    0.06
    sub
    0.06
    Act Density 0.076%

    No Known Activations