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

    Neuronpedia

    INDEX
    Explanations

    code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    PROJECT
    -0.07
    _IDS
    -0.07
    列
    -0.06
    THIS
    -0.06
    	wait
    -0.06
    )`
    -0.06
    ):
↵
    -0.06
    _To
    -0.06
    resolver
    -0.06
    .choice
    -0.06
    POSITIVE LOGITS
    =read
    0.07
    forming
    0.07
    .DeepEqual
    0.06
    ooter
    0.06
    zsche
    0.06
    erece
    0.06
    idelity
    0.06
     Crawford
    0.06
    ��
    0.06
     pars
    0.06
    Act Density 0.000%

    No Known Activations