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

    Neuronpedia

    INDEX
    Explanations

    marking territory

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ИС
    0.51
    kę
    0.50
    エム
    0.49
     μεγ
    0.49
     ζ
    0.48
     εργ
    0.48
     κο
    0.48
    יל
    0.46
     obliterated
    0.46
    ΑΣ
    0.46
    POSITIVE LOGITS
    Motivation
    0.47
    Widget
    0.47
    an
    0.46
    Quantity
    0.46
    Potion
    0.46
    i
    0.44
    Entropy
    0.43
    脆弱
    0.43
     t
    0.43
    刺激
    0.43
    Act Density 0.000%

    No Known Activations