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

    Neuronpedia

    INDEX
    Explanations

    'use

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ratulations
    -0.08
    contained
    -0.06
    help
    -0.06
     assembled
    -0.06
     possess
    -0.06
    LM
    -0.06
    ASF
    -0.06
    OA
    -0.06
     inventor
    -0.06
    -score
    -0.06
    POSITIVE LOGITS
    'use
    0.08
     PB
    0.07
     instrumentation
    0.07
    /*↵↵
    0.07
     assertFalse
    0.06
    막
    0.06
    ’un
    0.06
     mindfulness
    0.06
     #↵↵
    0.06
    */↵↵
    0.06
    Act Density 0.000%

    No Known Activations