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

    Neuronpedia

    INDEX
    Explanations

    malfunctions and errors

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     lever
    -0.07
    buscar
    -0.07
    拿到了
    -0.07
    Available
    -0.07
     Clerk
    -0.07
     outdated
    -0.07
    _advanced
    -0.07
     Adv
    -0.07
    交通安全
    -0.07
    座谈会
    -0.07
    POSITIVE LOGITS
    흟
    0.07
    깞
    0.07
    URRE
    0.07
    𝔞
    0.07
    {{$
    0.06
    gamma
    0.06
    🇿
    0.06
    엾
    0.06
    𝒉
    0.06
    �
    0.06
    Act Density 0.023%

    No Known Activations