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

    Neuronpedia

    INDEX
    Explanations

    output report, GPU time, Japan

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    helan
    0.49
    itió
    0.43
    ención
    0.43
    curr
    0.42
    zl
    0.42
     Gym
    0.40
    plete
    0.39
     ihrer
    0.38
     Indore
    0.38
    ósz
    0.38
    POSITIVE LOGITS
     disponibil
    0.51
    乸
    0.48
    பசு
    0.44
     neuroscience
    0.42
     sevgili
    0.42
    മി
    0.42
    バッグ
    0.41
    egas
    0.41
     कैल्शियम
    0.41
    婍
    0.41
    Act Density 0.000%

    No Known Activations