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

    Neuronpedia

    INDEX
    Explanations

    :

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    omnia
    -0.07
     cocktails
    -0.06
    .menu
    -0.06
     scanner
    -0.06
    伏
    -0.06
     scan
    -0.06
    _Enter
    -0.06
     drink
    -0.06
     scientist
    -0.06
    620
    -0.06
    POSITIVE LOGITS
    Alg
    0.07
    daq
    0.07
     -----
    0.07
     هد
    0.07
     hvě
    0.06
    |:
    0.06
    STEM
    0.06
    融
    0.06
     našich
    0.06
    lerdir
    0.06
    Act Density 0.006%

    No Known Activations