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

    Neuronpedia

    INDEX
    Explanations

    than

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    iddled
    -0.07
    нів
    -0.06
    _click
    -0.06
     Santana
    -0.06
    сылки
    -0.06
    uffers
    -0.06
    ştır
    -0.06
    行政
    -0.06
     contar
    -0.06
    	items
    -0.06
    POSITIVE LOGITS
    _RD
    0.06
     harb
    0.06
     工
    0.06
    WOOD
    0.06
     شهرد
    0.06
     poker
    0.05
    ther
    0.05
    _TIMEOUT
    0.05
    |=↵
    0.05
    -acre
    0.05
    Act Density 0.064%

    No Known Activations