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

    Neuronpedia

    INDEX
    Explanations

    it's

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     aspects
    -0.08
    ierung
    -0.08
     persuasive
    -0.08
    а
    -0.07
     triang
    -0.07
     Hess
    -0.07
    所谓
    -0.07
    体现
    -0.07
    ឹក
    -0.07
     retrospective
    -0.07
    POSITIVE LOGITS
     whisk
    0.09
     heaven
    0.08
    -ton
    0.08
     chatter
    0.08
    ------------------------------------------------
    0.08
     takk
    0.08
    mob
    0.08
     Owl
    0.08
     remedies
    0.07
     hadi
    0.07
    Act Density 0.092%

    No Known Activations