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

    Neuronpedia

    INDEX
    Explanations

    process.env

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     destacan
    0.43
     ಪ್ರಕಾರ
    0.41
     skut
    0.40
     cakkh
    0.40
     webpack
    0.40
    ेक्स
    0.40
     इश्
    0.38
    གས་
    0.38
     LOCCTR
    0.38
     ಆರಂಭ
    0.38
    POSITIVE LOGITS
     Beautiful
    0.50
     Greenwich
    0.44
     Immaculate
    0.42
    Beautiful
    0.41
     Herb
    0.41
     Greek
    0.41
    dea
    0.40
    繆
    0.40
     beautiful
    0.40
     प्या
    0.39
    Act Density 0.000%

    No Known Activations