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

    Neuronpedia

    INDEX
    Explanations

    Rocket propulsion

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     larg
    -0.07
    Liv
    -0.07
    bef
    -0.07
    iac
    -0.07
     wors
    -0.07
     specimen
    -0.07
     fac
    -0.06
     Smash
    -0.06
    wiąz
    -0.06
    咱们
    -0.06
    POSITIVE LOGITS
    체
    0.07
     ACA
    0.07
    🔑
    0.07
     אנ
    0.06
    (<
    0.06
    /categories
    0.06
    .LENGTH
    0.06
     الأن
    0.06
     SCP
    0.06
    時点
    0.06
    Act Density 0.014%

    No Known Activations