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

    Neuronpedia

    INDEX
    Explanations

    foreign languages

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Vermont
    -0.07
     الدولة
    -0.07
    endment
    -0.07
    INLINE
    -0.06
     legit
    -0.06
    Directory
    -0.06
    /video
    -0.06
    _SEARCH
    -0.06
     NORTH
    -0.06
    AIT
    -0.06
    POSITIVE LOGITS
     เร
    0.07
     Mot
    0.07
     připom
    0.06
    _CAM
    0.06
     jun
    0.06
     nuestros
    0.06
     Ap
    0.06
     요구
    0.06
     společně
    0.06
    訴
    0.06
    Act Density 1.203%

    No Known Activations