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

    Neuronpedia

    INDEX
    Explanations

    want

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .
↵
    -0.07
    קיב
    -0.07
     נת
    -0.07
    depth
    -0.07
    첵
    -0.07
     tedious
    -0.07
     дерев
    -0.07
     Steering
    -0.06
     Jaune
    -0.06
    노동
    -0.06
    POSITIVE LOGITS
     explode
    0.08
    ู
    0.07
    史上
    0.07
     Videos
    0.06
     bloc
    0.06
    pus
    0.06
    backend
    0.06
    府
    0.06
    華
    0.06
    _upper
    0.06
    Act Density 0.078%

    No Known Activations