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

    Neuronpedia

    INDEX
    Explanations

    gaining control

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     flattened
    -0.08
     macam
    -0.07
     inverse
    -0.07
     માટે
    -0.07
     shrink
    -0.07
    Shrink
    -0.07
     отвер
    -0.06
     flat
    -0.06
     artificial
    -0.06
    hausen
    -0.06
    POSITIVE LOGITS
     कब्ज
    0.13
     territ
    0.11
     victory
    0.11
     территории
    0.11
     possession
    0.10
     territorio
    0.10
     occupy
    0.10
     Territory
    0.10
     террит
    0.10
     власть
    0.10
    Act Density 0.065%

    No Known Activations