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

    Neuronpedia

    INDEX
    Explanations

    holding, gripping, clutching objects

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    дық
    0.48
    大規模
    0.42
     રાજ
    0.40
     गुस्
    0.40
    histor
    0.39
    હેરા
    0.39
    hiddenMap
    0.39
    睞
    0.39
     என்பதை
    0.38
     zej
    0.38
    POSITIVE LOGITS
     hold
    1.22
     holding
    1.16
     holds
    1.13
    hold
    1.06
     Hold
    1.06
     Holding
    1.01
     HOLD
    0.99
    Holding
    0.99
    Hold
    0.98
    holding
    0.95
    Act Density 0.029%

    No Known Activations