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

    Neuronpedia

    INDEX
    Explanations

    file paths and directories

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Rother
    0.31
    scott
    0.30
    0.29
    roasted
    0.28
    mo
    0.28
     أحد
    0.28
     रोजी
    0.28
    谱
    0.28
    phonic
    0.28
     Dove
    0.27
    POSITIVE LOGITS
     erstellen
    0.41
    捚
    0.39
    㚣
    0.38
     সরানো
    0.37
    algorith
    0.36
     완전
    0.35
     amortization
    0.35
    واعد
    0.34
    焲
    0.34
     debugging
    0.33
    Act Density 0.024%

    No Known Activations