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

    Neuronpedia

    INDEX
    Explanations

    code snippets

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    åĭĻ
    -0.27
     Arb
    -0.26
    andise
    -0.25
    ulla
    -0.25
    ·»
    -0.24
     interés
    -0.24
     arma
    -0.24
    æĶ¯åĩº
    -0.23
    arie
    -0.23
    utivo
    -0.23
    POSITIVE LOGITS
    ä¸įè¦ģ太
    0.32
    omers
    0.25
    fony
    0.24
    richt
    0.24
     Validates
    0.24
    rob
    0.24
    Validators
    0.24
     tack
    0.24
    èľ
    0.24
    StackSize
    0.24
    Act Density 0.066%

    No Known Activations