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

    Neuronpedia

    INDEX
    Explanations

    sensitization

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    :get
    -0.07
    lify
    -0.07
     tasted
    -0.07
     compliant
    -0.07
    κρα
    -0.07
     getLocation
    -0.06
     stores
    -0.06
     breathe
    -0.06
     IllegalStateException
    -0.06
     timers
    -0.06
    POSITIVE LOGITS
     beef
    0.06
     읽
    0.06
    KC
    0.06
     wys
    0.06
    ecx
    0.06
     datingsider
    0.06
    едини
    0.06
    pcf
    0.06
     зависит
    0.06
     believable
    0.06
    Act Density 0.006%

    No Known Activations