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

    Neuronpedia

    INDEX
    Explanations

    New Hampshire, NH

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ส
    0.86
    ม
    0.78
    م
    0.74
    м
    0.70
     AR
    0.68
    ق
    0.68
     Saclay
    0.66
    ย
    0.66
     mendapat
    0.64
     phosph
    0.64
    POSITIVE LOGITS
    Object
    0.65
    好
    0.64
    iece
    0.64
    oll
    0.63
    holds
    0.63
    roc
    0.62
    Path
    0.60
    LV
    0.59
    UT
    0.58
    Location
    0.58
    Act Density 0.001%

    No Known Activations