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

    Neuronpedia

    INDEX
    Explanations

    language identifiers

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    示例
    0.44
     thiol
    0.44
     sample
    0.43
     taper
    0.43
     végét
    0.42
     consume
    0.41
     virtud
    0.41
     amplitud
    0.40
     popOperand
    0.40
     urin
    0.40
    POSITIVE LOGITS
    માં
    0.47
    už
    0.43
     निवड
    0.43
    હે
    0.42
    २०
    0.41
    બે
    0.39
    म्ह
    0.38
     आपल्या
    0.38
    Задача
    0.38
    દ
    0.38
    Act Density 3.844%

    No Known Activations