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

    Neuronpedia

    INDEX
    Explanations

    3 or 4

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    <dd
    -0.08
    🏇
    -0.07
    蘸
    -0.07
     משר
    -0.07
    _learn
    -0.07
    (KEY
    -0.07
     expert
    -0.07
    skb
    -0.07
    腒
    -0.07
    🆂
    -0.07
    POSITIVE LOGITS
     bathroom
    0.07
    𑘁
    0.07
     sadly
    0.07
     impossible
    0.07
    فلسطين
    0.07
    防止
    0.07
     anonymity
    0.07
     temporary
    0.06
     District
    0.06
     sanctuary
    0.06
    Act Density 0.001%

    No Known Activations