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

    Neuronpedia

    INDEX
    Explanations

    ERICA

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     inaug
    -0.06
    ६
    -0.06
     fem
    -0.06
     visa
    -0.06
    ackage
    -0.06
    벽
    -0.06
    /';↵↵
    -0.06
    ̈
    -0.06
     curious
    -0.06
     relieve
    -0.06
    POSITIVE LOGITS
    _fre
    0.07
    masını
    0.07
    hoa
    0.06
     fakt
    0.06
    acterial
    0.06
    赢
    0.06
    ynchronously
    0.06
        
    0.06
    enci
    0.06
    TI
    0.06
    Act Density 0.009%

    No Known Activations