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

    Neuronpedia

    INDEX
    Explanations

    scope

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     ci
    -0.06
    лені
    -0.06
    ";↵
    -0.06
     чому
    -0.06
    	selected
    -0.06
    铺
    -0.06
    (lista
    -0.06
    漏
    -0.06
     outgoing
    -0.06
     откры
    -0.06
    POSITIVE LOGITS
     challenger
    0.07
     challeng
    0.07
     god
    0.06
    pulse
    0.06
     Ended
    0.06
    male
    0.06
    alloc
    0.06
     impart
    0.06
    PLEX
    0.06
     McK
    0.06
    Act Density 0.005%

    No Known Activations