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

    Neuronpedia

    INDEX
    Explanations

    percentage

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ieu
    -0.08
     Ts
    -0.07
    られる
    -0.07
     saldır
    -0.07
    Patient
    -0.06
     durante
    -0.06
    quivos
    -0.06
    警
    -0.06
    �
    -0.06
    jquery
    -0.06
    POSITIVE LOGITS
     sockfd
    0.07
    難
    0.07
     Directions
    0.06
     ghetto
    0.06
    .auto
    0.06
     popularity
    0.06
    (math
    0.06
    +',
    0.06
    }")
↵
    0.06
    __':↵
    0.06
    Act Density 0.013%

    No Known Activations