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

    Neuronpedia

    INDEX
    Explanations

    like

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Height
    -0.06
    elivery
    -0.06
    Farm
    -0.06
    Us
    -0.06
    hcp
    -0.06
    _CONTROL
    -0.06
    _RADIUS
    -0.06
     Україна
    -0.06
    處
    -0.06
    lfw
    -0.06
    POSITIVE LOGITS
     Cry
    0.07
    +x
    0.07
    #__
    0.07
     satisfies
    0.07
     concentrates
    0.06
     cry
    0.06
     correct
    0.06
     Мож
    0.06
     define
    0.06
     quaternion
    0.06
    Act Density 0.032%

    No Known Activations