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

    Neuronpedia

    INDEX
    Explanations

    Directory or project build commands

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     amplified
    -0.07
     Gors
    -0.07
    스테
    -0.06
     Sampler
    -0.06
    -reaching
    -0.06
    oğlu
    -0.06
    omers
    -0.06
    输
    -0.06
     Threshold
    -0.06
     Acceler
    -0.06
    POSITIVE LOGITS
    <![
    0.07
    Streams
    0.07
     eventType
    0.06
    .fast
    0.06
     \"
    0.06
     karak
    0.06
    ><?=$
    0.06
    auth
    0.06
    iddleware
    0.06
    �체
    0.06
    Act Density 0.010%

    No Known Activations