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

    Neuronpedia

    INDEX
    Explanations

    alumni

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ิโล
    -0.07
     rack
    -0.07
    sword
    -0.07
    ันเป
    -0.07
     Pit
    -0.07
    狐
    -0.06
    Boxes
    -0.06
     Cutter
    -0.06
     sheets
    -0.06
    .any
    -0.06
    POSITIVE LOGITS
    โย
    0.06
    -grade
    0.06
     allure
    0.06
     eventually
    0.06
     wisely
    0.06
     depreci
    0.06
     otev
    0.06
    983
    0.06
    alarm
    0.06
    _stdio
    0.06
    Act Density 0.002%

    No Known Activations