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

    Neuronpedia

    INDEX
    Explanations

    RMS

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    avacanam
    0.47
     demographic
    0.46
     bedtime
    0.46
     orthodontic
    0.45
    ojana
    0.45
     adolescents
    0.44
     autonomic
    0.44
     etiology
    0.44
     población
    0.43
     बच्चों
    0.43
    POSITIVE LOGITS
    guy
    0.43
    h
    0.42
    Paul
    0.42
    p
    0.42
    America
    0.41
    ಔ
    0.41
    ف
    0.41
    revolution
    0.41
    hz
    0.40
    T
    0.40
    Act Density 0.005%

    No Known Activations