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

    Neuronpedia

    INDEX
    Explanations

    problem-solving guidance

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Dan
    -0.07
     calcular
    -0.06
     graduate
    -0.06
     Vin
    -0.06
     lonely
    -0.06
    esthesia
    -0.06
     inhal
    -0.06
     bots
    -0.06
    contributors
    -0.06
    Indiana
    -0.06
    POSITIVE LOGITS
     leasing
    0.07
    abbage
    0.06
     týd
    0.06
    _LEG
    0.06
    _CM
    0.06
     Celebr
    0.06
     JOIN
    0.06
    _self
    0.06
    icking
    0.06
    anship
    0.06
    Act Density 0.158%

    No Known Activations