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

    Neuronpedia

    INDEX
    Explanations

    colon

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    	head
    -0.07
     resultados
    -0.07
     conquer
    -0.07
    閉
    -0.06
    perator
    -0.06
    _Release
    -0.06
     cuales
    -0.06
    执
    -0.06
    锁
    -0.06
     sprintf
    -0.06
    POSITIVE LOGITS
    ;">
↵
    0.06
    Alive
    0.06
     christmas
    0.06
     Jar
    0.06
    ç
    0.06
    0.06
    [@
    0.06
     ach
    0.06
     о
    0.06
    interesting
    0.06
    Act Density 0.008%

    No Known Activations