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

    Neuronpedia

    INDEX
    Explanations

    fightthenewdrug.org and harmful effects

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     somewhat
    0.46
     counseling
    0.44
     status
    0.42
     journaling
    0.41
     therapy
    0.40
     terapeut
    0.40
     priest
    0.39
     নিত
    0.39
     occasionally
    0.39
    偶尔
    0.39
    POSITIVE LOGITS
     harms
    0.54
     destabil
    0.53
     zwycię
    0.50
    icznej
    0.48
     inhuman
    0.48
     injustice
    0.47
     undermines
    0.46
     harmful
    0.45
    beatable
    0.45
     needlessly
    0.45
    Act Density 0.057%

    No Known Activations