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

    Neuronpedia

    INDEX
    Explanations

    Code/technical writing

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ycz
    -0.07
    esiz
    -0.07
    -away
    -0.07
     lah
    -0.07
     Got
    -0.06
    833
    -0.06
     DAR
    -0.06
    eree
    -0.06
     Ashton
    -0.06
     neod
    -0.06
    POSITIVE LOGITS
    (mean
    0.07
    (character
    0.07
    />
↵
    0.06
     Telefon
    0.06
    [loc
    0.06
     Innovation
    0.06
     Micro
    0.06
     innovation
    0.06
    (Environment
    0.06
    (rep
    0.06
    Act Density 0.003%

    No Known Activations