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

    Neuronpedia

    INDEX
    Explanations

    storage items

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     публика
    0.91
     galvanometer
    0.86
     tendo
    0.85
    한
    0.83
     malfunction
    0.82
     מאוד
    0.82
     virtualization
    0.81
     problemática
    0.80
     rumbo
    0.79
     बजकर
    0.79
    POSITIVE LOGITS
    𝗿
    0.88
    і
    0.87
    برای
    0.84
    ი
    0.84
    ir
    0.83
    udur
    0.83
    ie
    0.79
    ikiem
    0.77
    ों
    0.75
    for
    0.75
    Act Density 0.040%

    No Known Activations