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

    Neuronpedia

    INDEX
    Explanations

    the

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _depth
    -0.07
    (step
    -0.07
     muttered
    -0.07
    ấn
    -0.07
     utiliza
    -0.06
    --+
    -0.06
     modeled
    -0.06
     Emil
    -0.06
     ฟร
    -0.06
    อม
    -0.06
    POSITIVE LOGITS
    жди
    0.07
     Wheeler
    0.06
     twentieth
    0.06
    電視
    0.06
    стре
    0.06
    ς
    0.06
    Ξ
    0.06
     кисл
    0.06
    ("").
    0.06
    BSITE
    0.06
    Act Density 0.020%

    No Known Activations