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

    Neuronpedia

    INDEX
    Explanations

    therapy

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     therapy
    -1.70
     Therapy
    -1.70
    Therapy
    -1.66
     THERAPY
    -1.52
    therapy
    -1.51
     Therap
    -1.09
     terapia
    -1.04
     terapé
    -1.00
     therap
    -0.99
     therapist
    -0.98
    POSITIVE LOGITS
     of
    0.60
    .
    0.59
     to
    0.56
     in
    0.50
     with
    0.50
     for
    0.49
    em
    0.47
    ama
    0.46
    im
    0.46
    ;
    0.45
    Act Density 0.099%

    No Known Activations