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

    Neuronpedia

    INDEX
    Explanations

    names

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     myſelf
    -0.64
     himſelf
    -0.57
     chofe
    -0.57
     diſt
    -0.56
     zelve
    -0.55
     Scores
    -0.54
     themſelves
    -0.54
    sphase
    -0.54
     voisins
    -0.54
     Advice
    -0.53
    POSITIVE LOGITS
    iastes
    0.63
    ]")]
    0.60
    yard
    0.57
    marks
    0.56
    WriteTagHelper
    0.55
    wards
    0.54
    Xna
    0.54
    antry
    0.54
    wall
    0.53
    ward
    0.53
    Act Density 1.028%

    No Known Activations