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

    Neuronpedia

    INDEX
    Explanations

    Setting goals/boundaries

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _dir
    -0.08
     الأستاذ
    -0.08
    ubes
    -0.08
     Debido
    -0.07
    _stmt
    -0.07
    tsch
    -0.07
    umnos
    -0.07
    _cube
    -0.07
     garantizar
    -0.07
    _repr
    -0.07
    POSITIVE LOGITS
     cravings
    0.12
    戒
    0.11
     detox
    0.10
     remorse
    0.10
     CBT
    0.10
     craving
    0.10
     cessation
    0.10
     gradual
    0.09
     sobri
    0.09
     counseling
    0.09
    Act Density 0.018%

    No Known Activations