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

    Neuronpedia

    INDEX
    Explanations

    currently writing or preparing

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     buggy
    0.30
    ‍♀️
    0.28
    ‍♂️
    0.28
     식으로
    0.27
    ）
    0.27
    生地
    0.27
     گئے
    0.26
     మై
    0.26
    роваться
    0.26
     obej
    0.26
    POSITIVE LOGITS
     currently
    0.63
     Currently
    0.50
    currently
    0.50
     atualmente
    0.49
    Currently
    0.48
     finalizing
    0.48
     preparing
    0.47
     exploring
    0.46
     derzeit
    0.46
     attualmente
    0.45
    Act Density 0.010%

    No Known Activations