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

    Neuronpedia

    INDEX
    Explanations

    requires devices

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Dent
    0.53
    Athlete
    0.51
    Universal
    0.50
    Usually
    0.47
    Oregon
    0.45
    Study
    0.45
    Typically
    0.44
    0.44
    iPhone
    0.43
    Stud
    0.42
    POSITIVE LOGITS
     classifica
    0.55
     Pourquoi
    0.53
    prü
    0.50
     ennen
    0.49
    uparavant
    0.49
     Où
    0.48
     obscur
    0.47
     étapes
    0.46
     ök
    0.46
     další
    0.46
    Act Density 0.003%

    No Known Activations