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

    Neuronpedia

    INDEX
    Explanations

    mental health professionals

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     enmity
    0.39
     onslaught
    0.37
     eventful
    0.37
     asesin
    0.36
     bloodshed
    0.35
     並
    0.35
     requestCode
    0.34
     killings
    0.34
     monstros
    0.34
     為
    0.33
    POSITIVE LOGITS
     therapist
    0.55
     experts
    0.52
     psychologists
    0.49
     trusted
    0.48
     специалистов
    0.48
    كتب
    0.48
     gurus
    0.47
     specialists
    0.47
     psychologist
    0.47
    experts
    0.46
    Act Density 0.194%

    No Known Activations