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

    Neuronpedia

    INDEX
    Explanations

    siblings

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    /k
    -0.07
     Πολ
    -0.06
     drum
    -0.06
    ),↵↵
    -0.06
    ussian
    -0.06
    .Enum
    -0.06
    vens
    -0.06
    },↵↵
    -0.06
    );↵↵
    -0.06
    ↵↵↵↵
    -0.06
    POSITIVE LOGITS
    ظمة
    0.07
    	system
    0.06
    .ipv
    0.06
    _children
    0.06
    paring
    0.06
     electronics
    0.06
     writers
    0.06
    �
    0.06
     nhẹ
    0.06
    ldap
    0.06
    Act Density 0.265%

    No Known Activations