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

    Neuronpedia

    INDEX
    Explanations

    console

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     messages
    0.43
     sayings
    0.42
     unclaimed
    0.40
     entailed
    0.39
     Messages
    0.39
     bilgis
    0.39
     entail
    0.39
     dependant
    0.39
     Photoshop
    0.38
    inputValue
    0.38
    POSITIVE LOGITS
    Collecting
    0.44
     заболе
    0.39
    ]}$
    0.38
    భవ
    0.38
     להת
    0.36
     フランス
    0.35
     ব্যথা
    0.35
    Locks
    0.35
    }]\
    0.35
     Парт
    0.35
    Act Density 0.002%

    No Known Activations