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

    Neuronpedia

    INDEX
    Explanations

    major projects and campaigns

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    enes
    0.41
    ۲
    0.39
    с
    0.38
    os
    0.37
    2
    0.37
    Runtime
    0.36
    ens
    0.36
    3
    0.36
    ika
    0.36
    ۳
    0.36
    POSITIVE LOGITS
     efforts
    0.48
    in
    0.44
    i
    0.44
     onslaught
    0.41
     esfuerzos
    0.40
     esemplari
    0.40
     undertaken
    0.39
     inhale
    0.39
     взя
    0.38
     amplo
    0.38
    Act Density 0.168%

    No Known Activations