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

    Neuronpedia

    INDEX
    Explanations

    environment

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     মাম
    -0.09
     Halifax
    -0.08
    τό
    -0.08
     Geno
    -0.08
     solicitation
    -0.07
     altera
    -0.07
    来到
    -0.07
    Commun
    -0.07
     outright
    -0.07
     Hap
    -0.07
    POSITIVE LOGITS
     eingerichtet
    0.11
     scripts
    0.09
     setup
    0.08
     setups
    0.08
    setup
    0.08
    .setup
    0.08
     installiert
    0.08
     caring
    0.07
     penso
    0.07
     vair
    0.07
    Act Density 0.004%

    No Known Activations