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

    Neuronpedia

    INDEX
    Explanations

    classification of preceding words

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     MODKEY
    0.48
     ሽፋ
    0.47
     ice
    0.46
    ینے
    0.46
     ንጥረ
    0.45
     χρώ
    0.44
     sku
    0.44
    鳗
    0.43
    썽
    0.43
    尘
    0.43
    POSITIVE LOGITS
    تهم
    0.47
    your
    0.47
    pe
    0.45
    geri
    0.44
    delete
    0.43
    ir
    0.42
    isas
    0.42
    target
    0.41
    republik
    0.40
    ang
    0.40
    Act Density 0.010%

    No Known Activations