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

    Neuronpedia

    INDEX
    Explanations

    our

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    辉
    -0.08
     bevat
    -0.08
     plugin
    -0.08
     magnitude
    -0.08
     amplification
    -0.07
     curvature
    -0.07
     amplify
    -0.07
     enhancement
    -0.07
     útil
    -0.07
     particle
    -0.07
    POSITIVE LOGITS
     relaxed
    0.16
    舒服
    0.12
     расслаб
    0.12
     casual
    0.12
     lounging
    0.12
     relax
    0.12
    舒
    0.11
     pajamas
    0.11
     уют
    0.11
    Relax
    0.11
    Act Density 0.039%

    No Known Activations