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

    Neuronpedia

    INDEX
    Explanations

    Tried everything

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    riangle
    -0.09
     喜
    -0.08
     queremos
    -0.08
    喜
    -0.08
    喜欢
    -0.08
     আনন্দ
    -0.08
     enje
    -0.07
     hamar
    -0.07
    ownie
    -0.07
     nader
    -0.07
    POSITIVE LOGITS
     unsuccess
    0.16
     attempts
    0.14
     unsuccessful
    0.14
    Attempts
    0.14
     attempted
    0.13
     પ્રયાસ
    0.13
     tried
    0.13
     Attempts
    0.12
     Tried
    0.12
    尝
    0.12
    Act Density 0.083%

    No Known Activations