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

    Neuronpedia

    INDEX
    Explanations

    Math equations

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    🈯
    -0.07
    PEndPoint
    -0.06
     Staples
    -0.06
    🖋
    -0.06
    ⒟
    -0.06
     Bip
    -0.06
     Lav
    -0.06
    𬬩
    -0.06
     Mitarbeiter
    -0.06
    пряжен
    -0.06
    POSITIVE LOGITS
     bund
    0.08
    雄
    0.07
    毒
    0.07
    ий
    0.07
    �
    0.07
    教學
    0.07
    稱
    0.07
     ahead
    0.07
    ":["
    0.07
    >D
    0.07
    Act Density 0.005%

    No Known Activations