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

    Neuronpedia

    INDEX
    Explanations

    cancel

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    structure
    -0.07
     pinpoint
    -0.07
    (dp
    -0.07
     ud
    -0.06
    Practice
    -0.06
     RT
    -0.06
    itation
    -0.06
     rods
    -0.06
     trained
    -0.06
     Testament
    -0.06
    POSITIVE LOGITS
     cancell
    0.07
     cancel
    0.07
    mic
    0.07
    cancel
    0.07
    avatel
    0.07
    (Collision
    0.07
    unge
    0.07
    anol
    0.06
     remodel
    0.06
    ميل
    0.06
    Act Density 0.006%

    No Known Activations