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

    Neuronpedia

    INDEX
    Explanations

    the

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .tool
    -0.07
     Matchers
    -0.07
    aksi
    -0.07
     spectral
    -0.06
    output
    -0.06
     hoàn
    -0.06
    گیرد
    -0.06
    ions
    -0.06
    xford
    -0.06
    gua
    -0.06
    POSITIVE LOGITS
     nag
    0.07
    (matrix
    0.07
    の中
    0.07
     очи
    0.06
     skyrocket
    0.06
     herald
    0.06
    BT
    0.06
    デ
    0.06
     حجم
    0.06
     disagree
    0.06
    Act Density 0.045%

    No Known Activations