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

    Neuronpedia

    INDEX
    Explanations

    actions and conditions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    った
    0.44
     hoist
    0.43
     nahil
    0.42
    /**
    0.42
    富士
    0.42
    Σ
    0.42
    },
    0.41
     osmosis
    0.41
    ikian
    0.41
     oblige
    0.41
    POSITIVE LOGITS
     学生
    0.45
     촬영
    0.45
     கார
    0.45
    modified
    0.44
    classified
    0.44
     பற
    0.44
     특정
    0.44
     бушлай
    0.43
     maaf
    0.43
    utebol
    0.43
    Act Density 0.005%

    No Known Activations