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

    Neuronpedia

    INDEX
    Explanations

    yes

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    敷
    -0.06
    nění
    -0.06
    -sama
    -0.06
    atif
    -0.06
     pursue
    -0.06
     phía
    -0.06
     slain
    -0.05
     pursued
    -0.05
     も
    -0.05
    -ro
    -0.05
    POSITIVE LOGITS
    yclerview
    0.07
     Jessie
    0.07
    ]);↵↵
    0.07
     зокрема
    0.07
    applications
    0.07
    оян
    0.06
    提示
    0.06
     dabei
    0.06
     filmer
    0.06
    "}↵↵
    0.06
    Act Density 0.018%

    No Known Activations