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

    Neuronpedia

    INDEX
    Explanations

    Book titles or excerpts

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    dni
    -0.07
    ном
    -0.07
    fy
    -0.06
    usion
    -0.06
    टक
    -0.06
     θεω
    -0.06
    SSF
    -0.06
    imus
    -0.06
     SHOW
    -0.06
     гип
    -0.06
    POSITIVE LOGITS
     drip
    0.07
     dob
    0.07
    _ins
    0.07
    '#
    0.07
     carcin
    0.06
     exagger
    0.06
     prospects
    0.06
     energ
    0.06
    ]");↵
    0.06
    Cut
    0.06
    Act Density 0.013%

    No Known Activations