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

    Neuronpedia

    INDEX
    Explanations

    he

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    	dto
    -0.07
    }`}↵
    -0.06
    弟
    -0.06
    .circular
    -0.06
     lig
    -0.06
    _flat
    -0.06
    еть
    -0.06
     ')';↵
    -0.06
    /download
    -0.06
    隆
    -0.05
    POSITIVE LOGITS
     poets
    0.07
    osp
    0.07
    이었
    0.06
    ToOne
    0.06
     ambush
    0.06
     Ini
    0.06
     complied
    0.06
     asylum
    0.06
     smashed
    0.06
     stimulating
    0.06
    Act Density 0.008%

    No Known Activations