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

    Neuronpedia

    INDEX
    Explanations

    vocal

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    xFA
    -0.07
    ayıf
    -0.06
    ledo
    -0.06
    _retry
    -0.06
    .currentPage
    -0.06
     raz
    -0.06
     Mädchen
    -0.06
     mente
    -0.06
     경기
    -0.06
    φερ
    -0.06
    POSITIVE LOGITS
     outspoken
    0.10
     vehement
    0.08
     adamant
    0.07
    (Module
    0.07
     dramatically
    0.06
     say
    0.06
    mutable
    0.06
     activist
    0.06
     Umb
    0.06
     assertions
    0.06
    Act Density 0.011%

    No Known Activations