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

    Neuronpedia

    INDEX
    Explanations

    person

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Tec
    -0.07
    Matchers
    -0.06
     поэтому
    -0.06
     AN
    -0.06
     slows
    -0.06
    Anc
    -0.06
     Sco
    -0.06
     pelos
    -0.06
    /constants
    -0.06
     Destructor
    -0.06
    POSITIVE LOGITS
    :Boolean
    0.07
    ети
    0.07
    민주
    0.06
    eth
    0.06
    FR
    0.06
    agnosis
    0.06
    -written
    0.06
    ea
    0.06
    (poly
    0.06
    (error
    0.06
    Act Density 0.000%

    No Known Activations