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

    Neuronpedia

    INDEX
    Explanations

    infidelity, violence, harmful scenarios

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    SCUS
    0.43
    ruptcy
    0.43
    ANO
    0.42
    ESTER
    0.42
     বেশী
    0.42
     நிறைய
    0.42
     graag
    0.41
    norr
    0.41
    KOV
    0.40
     approximations
    0.40
    POSITIVE LOGITS
     toolkit
    0.51
    针对
    0.47
     Toolkit
    0.47
     Challenge
    0.44
     Tackle
    0.44
     callback
    0.41
     unexpected
    0.41
     Callback
    0.40
    娴
    0.39
     Fidelity
    0.39
    Act Density 0.041%

    No Known Activations