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

    Neuronpedia

    INDEX
    Explanations

    left

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    irds
    -0.09
    istes
    -0.09
     smokers
    -0.08
    (answer
    -0.07
     périodes
    -0.07
    ிகள்
    -0.07
    anng
    -0.07
    imbra
    -0.07
    icine
    -0.07
     Ond
    -0.07
    POSITIVE LOGITS
     postgres
    0.09
     "../../../
    0.09
     secluded
    0.09
     "../../
    0.08
     terminal
    0.08
    Terminal
    0.08
     "../../../../
    0.08
     stdin
    0.08
     quaint
    0.08
     ვიდეო
    0.08
    Act Density 0.000%

    No Known Activations