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

    Neuronpedia

    INDEX
    Explanations

    code snippets

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     оф
    -0.07
     holy
    -0.07
    鞴
    -0.07
     islands
    -0.06
    �
    -0.06
    ternal
    -0.06
    降幅
    -0.06
    IVED
    -0.06
    edly
    -0.06
    🏸
    -0.06
    POSITIVE LOGITS
     RPM
    0.09
     reiterated
    0.07
    说到这里
    0.07
    _wheel
    0.07
     projet
    0.07
    xB
    0.07
    	dist
    0.07
    *R
    0.06
    cerpt
    0.06
    進
    0.06
    Act Density 0.003%

    No Known Activations