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

    Neuronpedia

    INDEX
    Explanations

    CO

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     XM
    -0.07
     endings
    -0.07
     IDS
    -0.07
    `=
    -0.07
    好
    -0.07
     PARK
    -0.07
     봐
    -0.07
    EXP
    -0.06
    .expect
    -0.06
     dent
    -0.06
    POSITIVE LOGITS
    ieber
    0.07
    jec
    0.06
     irgend
    0.06
    öh
    0.06
    spir
    0.06
     Develop
    0.06
     dissent
    0.06
    phet
    0.06
    erli
    0.06
    /license
    0.05
    Act Density 0.002%

    No Known Activations