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

    Neuronpedia

    INDEX
    Explanations

    secrets, clickbait, and lists

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Rounds
    0.37
     tampilan
    0.34
     kamera
    0.34
     prinsip
    0.34
     다양한
    0.32
     ตัด
    0.32
     sangre
    0.32
     notepad
    0.32
     landlab
    0.32
     pelatihan
    0.32
    POSITIVE LOGITS
    d
    0.36
    crast
    0.34
    irting
    0.32
    Concerning
    0.31
    certain
    0.31
    advised
    0.30
    illos
    0.30
    industrial
    0.30
    <0x93>
    0.30
    reversible
    0.30
    Act Density 0.001%

    No Known Activations