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

    Neuronpedia

    INDEX
    Explanations

    sports, WWE, and lists

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Jeho
    -0.72
    歌唱
    -0.72
    ikai
    -0.70
    ropho
    -0.70
    Decl
    -0.70
     Bohr
    -0.69
     pianist
    -0.69
     FAILED
    -0.69
     TRANSFORM
    -0.68
    blins
    -0.68
    POSITIVE LOGITS
    stool
    1.14
    écrivain
    0.80
     stools
    0.79
     gambling
    0.78
    Ƒ
    0.77
    Sauce
    0.77
    kfree
    0.77
     Stool
    0.76
    Activities
    0.75
    ደ
    0.75
    Act Density 0.009%

    No Known Activations