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

    Neuronpedia

    INDEX
    Explanations

    construction

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    BindingUtil
    -0.08
     Suicide
    -0.07
     Dixon
    -0.06
     levitra
    -0.06
     Express
    -0.06
     IRS
    -0.06
     Adrian
    -0.06
    Tier
    -0.06
     entertainment
    -0.06
     Soul
    -0.06
    POSITIVE LOGITS
     DIST
    0.06
    _UNITS
    0.06
    :Register
    0.06
     Pipes
    0.06
     СРСР
    0.06
     nons
    0.06
     uns
    0.06
    （
    0.06
     структу
    0.06
    #w
    0.06
    Act Density 0.023%

    No Known Activations