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

    Neuronpedia

    INDEX
    Explanations

    Hebrew prefixes and suffixes

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Hond
    0.40
    дами
    0.39
     अट
    0.39
     pathetic
    0.39
     Link
    0.39
     യ
    0.38
    lesssim
    0.38
     Blom
    0.38
     અમ
    0.38
     sauté
    0.38
    POSITIVE LOGITS
    projectName
    0.40
    עה
    0.40
     همکاری
    0.39
    ירות
    0.38
    יל
    0.37
    рения
    0.36
    את
    0.36
    ariah
    0.36
    טת
    0.36
    ונה
    0.36
    Act Density 0.001%

    No Known Activations