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

    Neuronpedia

    INDEX
    Explanations

    Evaluation of something

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    亚
    -0.07
     RTWF
    -0.07
     ox
    -0.07
     newbie
    -0.07
    NodeType
    -0.06
    madan
    -0.06
     кри
    -0.06
     chauff
    -0.06
     architectures
    -0.06
    _Entry
    -0.06
    POSITIVE LOGITS
     aliens
    0.07
    Histor
    0.06
     serão
    0.06
     Banking
    0.06
    Module
    0.06
    那么
    0.06
    %S
    0.06
    อล
    0.06
     leurs
    0.06
    onnement
    0.06
    Act Density 0.833%

    No Known Activations