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

    Neuronpedia

    INDEX
    Explanations

    Neovim

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     older
    0.55
     workspace
    0.51
     hamster
    0.51
     workstation
    0.50
     brisket
    0.49
    itre
    0.49
     utilize
    0.48
     rotations
    0.48
     spaceship
    0.48
    appers
    0.48
    POSITIVE LOGITS
    avlja
    0.52
    ات
    0.47
    حدة
    0.46
    肱
    0.46
    酤
    0.46
    诰
    0.45
    促进
    0.45
    اي
    0.44
    linge
    0.44
    zocht
    0.44
    Act Density 0.000%

    No Known Activations