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

    Neuronpedia

    INDEX
    Explanations

    temporary endeavor

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     ιστο
    0.48
    onti
    0.48
    妏
    0.45
     পারছে
    0.44
    钀
    0.44
     CONNECTION
    0.43
    కున్న
    0.43
     нюан
    0.43
     specifiche
    0.42
    雳
    0.42
    POSITIVE LOGITS
    potential
    0.43
     मौसम
    0.42
     अनुशंसा
    0.41
    amos
    0.40
    MF
    0.40
     hlas
    0.40
     chấm
    0.39
    induced
    0.39
    Prior
    0.38
    Potential
    0.38
    Act Density 0.000%

    No Known Activations