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

    Neuronpedia

    INDEX
    Explanations

    life threatening

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     serendip
    0.41
    踌
    0.40
    Hes
    0.39
    രണം
    0.38
     DISCLAIM
    0.38
    াজী
    0.37
    romptu
    0.37
    ilage
    0.36
    唏
    0.36
    ahl
    0.36
    POSITIVE LOGITS
     threat
    4.03
    Threat
    3.86
     threats
    3.84
    threat
    3.73
     Threat
    3.67
     Threats
    3.61
    威胁
    3.55
     threaten
    3.53
     amea
    3.42
     threatening
    3.31
    Act Density 0.068%

    No Known Activations