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

    Neuronpedia

    INDEX
    Explanations

    Actions with consequences

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    	control
    -0.07
    /env
    -0.07
     \%
    -0.07
     усл
    -0.07
     go
    -0.06
    pure
    -0.06
     driver
    -0.06
    _role
    -0.06
     chan
    -0.06
    led
    -0.06
    POSITIVE LOGITS
     miesz
    0.07
     فس
    0.07
    inez
    0.06
    cych
    0.06
     متر
    0.06
    resize
    0.06
    (itemView
    0.06
    นคร
    0.06
    ☆
    0.06
     MCS
    0.06
    Act Density 0.517%

    No Known Activations