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

    Neuronpedia

    INDEX
    Explanations

    code and notations

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     massac
    -0.07
    plemented
    -0.07
    Male
    -0.07
     unab
    -0.07
    SES
    -0.07
    ік
    -0.07
     цар
    -0.07
     choses
    -0.06
     gj
    -0.06
     espa
    -0.06
    POSITIVE LOGITS
    ималь
    0.06
    ΟΦ
    0.06
     размещ
    0.06
    -complete
    0.06
    链
    0.06
    MHz
    0.06
    .");
↵
    0.06
    SBATCH
    0.06
    clared
    0.05
    .success
    0.05
    Act Density 0.002%

    No Known Activations