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

    Neuronpedia

    INDEX
    Explanations

    Location/group followed by punctuation

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    而言
    -0.07
    רת
    -0.07
     establish
    -0.06
     porr
    -0.06
    ceed
    -0.06
    وية
    -0.06
    �
    -0.06
    упить
    -0.06
    财力
    -0.06
     <-
    -0.06
    POSITIVE LOGITS
    	AM
    0.07
    𝐦
    0.07
    _PARSE
    0.06
     strangely
    0.06
    _CRYPTO
    0.06
    _tracking
    0.06
    packet
    0.06
    Variables
    0.06
     arrays
    0.06
     mp
    0.06
    Act Density 0.146%

    No Known Activations