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

    Neuronpedia

    INDEX
    Explanations

    The

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     kısm
    -0.07
     otáz
    -0.07
    ῆ
    -0.07
    ören
    -0.07
     stories
    -0.07
    ?↵↵↵↵↵↵
    -0.07
     '-')
    -0.06
     itself
    -0.06
     Sinh
    -0.06
    .Signal
    -0.06
    POSITIVE LOGITS
    .BLL
    0.06
     mlad
    0.06
    cheon
    0.05
    leted
    0.05
    igenous
    0.05
     gotten
    0.05
    automation
    0.05
     чуж
    0.05
    Confirmed
    0.05
    dit
    0.05
    Act Density 0.368%

    No Known Activations