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

    Neuronpedia

    INDEX
    Explanations

    punctuation

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     každé
    -0.07
    ля
    -0.07
     como
    -0.07
    一定
    -0.06
     облас
    -0.06
    以前
    -0.06
    Normally
    -0.06
    rý
    -0.06
     самый
    -0.06
     vše
    -0.06
    POSITIVE LOGITS
     participate
    0.07
     tangled
    0.07
    (path
    0.06
    130
    0.06
    unexpected
    0.06
    PMC
    0.06
    @JsonProperty
    0.06
     upgrading
    0.06
     unexpected
    0.06
    erah
    0.06
    Act Density 0.041%

    No Known Activations