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

    Neuronpedia

    INDEX
    Explanations

    flirty or cheesy questions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     July
    0.42
     general
    0.41
    ↵↵
    0.40
     online
    0.40
    )
    0.39
     inter
    0.38
    ]
    0.38
     domains
    0.38
     academic
    0.37
     cohort
    0.37
    POSITIVE LOGITS
    Didn
    0.57
    Doesn
    0.52
    Wouldn
    0.52
    Does
    0.52
    Honestly
    0.51
    Seriously
    0.50
    doesn
    0.49
     Wouldn
    0.49
     Didn
    0.48
    when
    0.48
    Act Density 0.015%

    No Known Activations