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

    Neuronpedia

    INDEX
    Explanations

    vill

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Fade
    -0.07
     Notes
    -0.07
     доп
    -0.06
     confident
    -0.06
    bike
    -0.06
    shots
    -0.06
    are
    -0.06
    te
    -0.06
     subtype
    -0.06
    ander
    -0.06
    POSITIVE LOGITS
    Thr
    0.07
     �
    0.06
     král
    0.06
     Carlson
    0.06
    бом
    0.06
    Sab
    0.06
    appoint
    0.06
    Messenger
    0.06
     todd
    0.06
    implicitly
    0.06
    Act Density 0.001%

    No Known Activations