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

    Neuronpedia

    INDEX
    Explanations

    kubernetes configurations

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     overlooking
    -0.07
    โต
    -0.07
    611
    -0.07
     Toggle
    -0.06
    详
    -0.06
     draft
    -0.06
    K
    -0.06
    ^K
    -0.06
    	↵↵
    -0.06
     '%"
    -0.06
    POSITIVE LOGITS
    بش
    0.07
     Appalach
    0.06
     исключ
    0.06
    (scope
    0.06
     asphalt
    0.06
    �
    0.06
    PTS
    0.06
    itra
    0.06
     rhetoric
    0.06
     Jeg
    0.06
    Act Density 0.008%

    No Known Activations