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

    Neuronpedia

    INDEX
    Explanations

    groove and variations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     GR
    0.50
     Grip
    0.50
     Гри
    0.50
     Gr
    0.49
     Gri
    0.47
     GRI
    0.46
     гри
    0.44
     Gris
    0.44
     Grac
    0.43
    Gr
    0.43
    POSITIVE LOGITS
    oving
    0.57
    tes
    0.56
    ove
    0.54
    oved
    0.53
    ovia
    0.53
    oves
    0.52
    oval
    0.50
    ov
    0.49
    ovno
    0.47
    ovy
    0.44
    Act Density 0.001%

    No Known Activations