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

    Neuronpedia

    INDEX
    Explanations

    encoding

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    igers
    -0.07
    ัฒน
    -0.06
    ائ
    -0.06
    zeit
    -0.06
    liste
    -0.06
    .ManyToManyField
    -0.06
     Theft
    -0.06
    IRECT
    -0.06
     Mü
    -0.06
    ária
    -0.06
    POSITIVE LOGITS
    "encoding
    0.14
     polarity
    0.07
    porn
    0.07
    >P
    0.07
    Version
    0.07
    845
    0.07
    generic
    0.06
     susceptible
    0.06
    -en
    0.06
     preference
    0.06
    Act Density 0.000%

    No Known Activations