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

    Neuronpedia

    INDEX
    Explanations

    code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     тип
    -0.06
     possibile
    -0.06
    (vol
    -0.06
     pals
    -0.06
    iage
    -0.06
     اليوم
    -0.06
     approach
    -0.06
     cellar
    -0.06
    ignon
    -0.05
     багать
    -0.05
    POSITIVE LOGITS
     mu
    0.07
    mares
    0.07
    chalk
    0.07
    ************************
    0.07
    REG
    0.07
     hippoc
    0.07
    circ
    0.06
     ним
    0.06
    arf
    0.06
    Fn
    0.06
    Act Density 0.005%

    No Known Activations