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

    Neuronpedia

    INDEX
    Explanations

    Datasets

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     percent
    -0.08
    _element
    -0.07
    Evaluate
    -0.07
    βά
    -0.07
    aland
    -0.07
     checks
    -0.07
    �
    -0.07
     watches
    -0.07
    >
↵
↵
    -0.07
    ad
    -0.07
    POSITIVE LOGITS
    .,
    0.06
    ecial
    0.06
     fulfilling
    0.06
     тор
    0.06
     �
    0.06
     asn
    0.06
     สำหร
    0.06
     Moff
    0.06
     McM
    0.06
     bồi
    0.06
    Act Density 0.058%

    No Known Activations