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

    Neuronpedia

    INDEX
    Explanations

    Narrative context

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    |min
    -0.07
    rado
    -0.07
    Direct
    -0.06
     عز
    -0.06
     Род
    -0.06
    .binary
    -0.06
    Personal
    -0.06
     함수
    -0.06
     日期
    -0.06
     Ethernet
    -0.06
    POSITIVE LOGITS
    –
    0.07
    ahun
    0.06
    ucchini
    0.06
    coeff
    0.06
    _／
    0.06
     Advertisement
    0.06
     unn
    0.06
     antique
    0.06
    about
    0.06
    (-
    0.06
    Act Density 0.051%

    No Known Activations