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

    Neuronpedia

    INDEX
    Explanations

    concepts driving actions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Č
    0.49
    Chrom
    0.47
    Oh
    0.47
    ERG
    0.42
    رفته
    0.40
    緩和
    0.40
    India
    0.40
    émica
    0.39
    Charl
    0.39
    생
    0.39
    POSITIVE LOGITS
     சிறந்த
    0.43
     целе
    0.40
    ರಿನ
    0.38
     lua
    0.38
     mappings
    0.38
     *);
    0.37
     सर्वश्रेष्ठ
    0.37
     плани
    0.37
    を選ぶ
    0.37
     td
    0.37
    Act Density 0.001%

    No Known Activations