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

    Neuronpedia

    INDEX
    Explanations

    Tense and energetic situations

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     touted
    -0.07
     цар
    -0.07
    atha
    -0.07
    ينية
    -0.06
     flush
    -0.06
     Spiral
    -0.06
     αυτή
    -0.06
    atown
    -0.06
    їна
    -0.06
     есте
    -0.06
    POSITIVE LOGITS
    Od
    0.06
     fright
    0.06
     ú
    0.06
    plitude
    0.06
    _male
    0.06
    =input
    0.06
    �
    0.06
     Od
    0.06
    <Renderer
    0.06
     revealing
    0.06
    Act Density 0.042%

    No Known Activations