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

    Neuronpedia

    INDEX
    Explanations

    investing heavily, investors eager

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     cares
    0.52
     stories
    0.48
     faithful
    0.47
     takes
    0.46
     constitution
    0.46
     atheros
    0.46
     texts
    0.46
     wild
    0.46
     other
    0.45
     strategies
    0.45
    POSITIVE LOGITS
    കൊ
    0.54
    ERR
    0.49
    伱
    0.47
    ма
    0.47
    ウエスト
    0.44
    饅
    0.44
    -=
    0.44
    対象
    0.44
    ORT
    0.43
    সহ
    0.43
    Act Density 0.001%

    No Known Activations