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

    Neuronpedia

    INDEX
    Explanations

    scientific/academic texts

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    gt
    -0.08
    告訴
    -0.07
    提及
    -0.07
    ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
    -0.07
     gained
    -0.07
    >Select
    -0.07
    ością
    -0.07
    ************************************************
    -0.07
    调侃
    -0.07
    atri
    -0.07
    POSITIVE LOGITS
     AppMethodBeat
    0.08
     debugger
    0.08
     inaugur
    0.07
     zahl
    0.07
     UserProfile
    0.07
     Greenland
    0.07
     deviceId
    0.07
    经开
    0.07
     matriz
    0.07
     bod
    0.07
    Act Density 0.272%

    No Known Activations