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

    Neuronpedia

    INDEX
    Explanations

    Django app configuration

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    rike
    -0.08
     behaved
    -0.08
    swift
    -0.07
     notoriously
    -0.07
    aining
    -0.07
    quat
    -0.07
    /entities
    -0.07
    judge
    -0.07
    𫐓
    -0.07
     środowisk
    -0.06
    POSITIVE LOGITS
    issippi
    0.07
    (completion
    0.07
    �
    0.07
     imp
    0.06
    lify
    0.06
    类产品
    0.06
    蘼
    0.06
    結
    0.06
     bal
    0.06
     Harry
    0.06
    Act Density 0.001%

    No Known Activations