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

    Neuronpedia

    INDEX
    Explanations

    Code snippets

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     rival
    -0.07
    _LINE
    -0.07
     acoustic
    -0.06
     번
    -0.06
    spNet
    -0.06
     semantic
    -0.06
    _brand
    -0.06
    δή
    -0.06
    olars
    -0.06
     trousers
    -0.06
    POSITIVE LOGITS
     jika
    0.07
     commuter
    0.07
    .Be
    0.06
     фундамент
    0.06
    _p
    0.06
     �
    0.06
    _fil
    0.06
    .uint
    0.06
    Attachment
    0.06
    ece
    0.06
    Act Density 0.005%

    No Known Activations