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

    Neuronpedia

    INDEX
    Explanations

    OF

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     otherwise
    -0.08
     UnityEditor
    -0.08
     adolescence
    -0.07
    Pa
    -0.07
    新业态
    -0.07
    rien
    -0.07
    渥
    -0.07
     opcode
    -0.07
     væ
    -0.07
     потому
    -0.07
    POSITIVE LOGITS
     (`
    0.07
    ``
    0.07
     broaden
    0.07
    ∼
    0.07
     정말
    0.07
    hf
    0.07
    ¯
    0.07
    那天
    0.07
     reassuring
    0.06
    =q
    0.06
    Act Density 0.001%

    No Known Activations