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

    Neuronpedia

    INDEX
    Explanations

    are

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     рос
    -0.06
     سن
    -0.06
    _ENTITY
    -0.06
     compared
    -0.06
    handles
    -0.06
    there
    -0.06
    torch
    -0.06
    фи
    -0.06
    oes
    -0.06
    ordinator
    -0.06
    POSITIVE LOGITS
    .↵↵↵↵↵
    0.07
    EditMode
    0.07
     sexuales
    0.06
     designate
    0.06
     restores
    0.06
    сім
    0.06
    Tonight
    0.06
     sued
    0.06
    美國
    0.06
    梦
    0.06
    Act Density 0.000%

    No Known Activations