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

    Neuronpedia

    INDEX
    Explanations

    lock

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     delimit
    -0.08
     misunderstanding
    -0.07
     communication
    -0.07
     window
    -0.07
     kommunik
    -0.07
     comunicar
    -0.07
     projections
    -0.07
     moon
    -0.07
     parsing
    -0.07
     projection
    -0.07
    POSITIVE LOGITS
     Arrest
    0.10
    _Control
    0.09
     Reb
    0.09
     പോലീസ്
    0.09
    254
    0.08
     Cross
    0.08
     جل
    0.08
     crackdown
    0.08
     Defender
    0.08
     corrective
    0.08
    Act Density 0.002%

    No Known Activations