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

    Neuronpedia

    INDEX
    Explanations

    developing immunity/tolerance

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     counselors
    -0.07
     Ratio
    -0.06
    _final
    -0.06
     rooms
    -0.06
    rijk
    -0.06
     »↵
    -0.06
     caret
    -0.06
     Desk
    -0.06
    》↵
    -0.06
    cılık
    -0.06
    POSITIVE LOGITS
     contingent
    0.07
     apresent
    0.07
     impaired
    0.06
    KEN
    0.06
    _DELTA
    0.06
    ="{!!
    0.06
    _PUSH
    0.06
     renown
    0.06
    -valu
    0.06
     повин
    0.06
    Act Density 0.042%

    No Known Activations