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

    Neuronpedia

    INDEX
    Explanations

    reaching for more

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    FBSDKError
    0.54
     unlabeled
    0.44
     polypeptides
    0.44
    DEPENDENCIA
    0.42
     meson
    0.41
     framebuffer
    0.41
     peptide
    0.41
     zyg
    0.41
    ")(
    0.41
     carcasses
    0.40
    POSITIVE LOGITS
     While
    0.50
     Being
    0.48
     Use
    0.44
    gré
    0.44
     We
    0.43
     Once
    0.43
     Men
    0.42
     Rockstar
    0.40
     It
    0.40
     Because
    0.39
    Act Density 0.002%

    No Known Activations