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

    Neuronpedia

    INDEX
    Explanations

    hard

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Flynn
    -0.06
    osta
    -0.06
     ofere
    -0.06
     Vert
    -0.06
    .Scene
    -0.06
    innitus
    -0.06
    겠
    -0.06
    озна
    -0.06
     susceptibility
    -0.06
     sublist
    -0.06
    POSITIVE LOGITS
     hard
    0.15
     Hard
    0.14
    Hard
    0.11
     harder
    0.09
    -hard
    0.09
    _hard
    0.09
    hard
    0.09
     HARD
    0.08
     Harding
    0.08
     hardened
    0.08
    Act Density 0.018%

    No Known Activations