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

    Neuronpedia

    INDEX
    Explanations

    neural networks

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    mium
    0.80
     сере
    0.72
     côtés
    0.71
    juvant
    0.71
    alled
    0.70
     entornos
    0.67
    刂
    0.66
     bereaved
    0.65
    報
    0.65
    ulpt
    0.65
    POSITIVE LOGITS
     neural
    1.85
     Neural
    1.82
    Neural
    1.79
    neural
    1.65
    神经网络
    0.98
    nonlinear
    0.75
     neuronal
    0.74
     Nonlinear
    0.74
    encoder
    0.73
    𝗍
    0.73
    Act Density 0.087%

    No Known Activations