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

    Neuronpedia

    INDEX
    Explanations

    Form

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    olars
    -0.07
     coolant
    -0.07
    อาย
    -0.06
     노
    -0.06
    ITAL
    -0.06
     loosen
    -0.06
    年代
    -0.06
    莫
    -0.06
    Yaw
    -0.06
    Live
    -0.06
    POSITIVE LOGITS
    (Form
    0.08
    form
    0.08
     Sphere
    0.07
    .Append
    0.07
    FORM
    0.07
    [string
    0.07
     Stephens
    0.07
     ilk
    0.06
     Mask
    0.06
    .Assertions
    0.06
    Act Density 0.020%

    No Known Activations