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

    Neuronpedia

    INDEX
    Explanations

    situation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    которы
    0.89
     walled
    0.88
     данный
    0.87
    ется
    0.86
    ủa
    0.85
    чность
    0.84
    }^{-\
    0.84
     picnics
    0.82
    h
    0.80
     greed
    0.80
    POSITIVE LOGITS
    US
    0.74
    solar
    0.73
    source
    0.72
    opera
    0.70
    omia
    0.70
    uration
    0.70
    AMES
    0.70
    tutorial
    0.69
    א
    0.69
    MAS
    0.68
    Act Density 0.000%

    No Known Activations