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

    Neuronpedia

    INDEX
    Explanations

    conjunctions

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    (where
    -0.06
     ontology
    -0.06
    (D
    -0.06
    (Post
    -0.06
    (string
    -0.06
    коном
    -0.06
    240
    -0.06
     widgets
    -0.06
    Domin
    -0.06
     weakened
    -0.06
    POSITIVE LOGITS
     Hiç
    0.07
     Muj
    0.07
    ="'+
    0.07
     ×
    0.07
     mũi
    0.06
    camera
    0.06
     Mey
    0.06
    lev
    0.06
    ';
↵
    0.06
    �
    0.06
    Act Density 0.081%

    No Known Activations