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

    Neuronpedia

    INDEX
    Explanations

    Direct address, instructions

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     autumn
    -0.07
     stumbled
    -0.07
     éxito
    -0.07
     Terminator
    -0.06
     bisexual
    -0.06
     demographics
    -0.06
     cualquier
    -0.06
    tanggal
    -0.06
    は
    -0.06
    去了
    -0.06
    POSITIVE LOGITS
    닝
    0.07
    [min
    0.07
    λέ
    0.06
    [x
    0.06
    [e
    0.06
    lrt
    0.06
    버지
    0.06
    astos
    0.06
    adní
    0.06
     EL
    0.06
    Act Density 0.056%

    No Known Activations