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

    Neuronpedia

    INDEX
    Explanations

    studies and experiments

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ±
    -0.07
    twenty
    -0.06
    million
    -0.06
     attributable
    -0.06
    fadeIn
    -0.06
    ABEL
    -0.06
     sin
    -0.06
    	container
    -0.06
    inscription
    -0.06
    €�
    -0.06
    POSITIVE LOGITS
    _pull
    0.07
    اقل
    0.07
    /dialog
    0.07
    .UNKNOWN
    0.07
    -ob
    0.06
    时候
    0.06
    없음
    0.06
    }()↵↵
    0.06
    isinin
    0.06
     reshape
    0.06
    Act Density 0.248%

    No Known Activations