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

    Neuronpedia

    INDEX
    Explanations

    emotional consequence after word

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     فونی
    0.41
    hlung
    0.38
     दाल
    0.37
     архівної
    0.37
    そも
    0.37
    álních
    0.36
    nj
    0.36
    ایج
    0.36
    琯
    0.36
    雓
    0.36
    POSITIVE LOGITS
    Steve
    0.47
     Steve
    0.47
    flight
    0.44
     manager
    0.43
     Spike
    0.42
    েব
    0.42
    bucket
    0.41
    sender
    0.40
     steve
    0.40
    Sp
    0.40
    Act Density 0.000%

    No Known Activations