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

    Neuronpedia

    INDEX
    Explanations

    code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    (str
    -0.08
    /_
    -0.07
    .accel
    -0.07
    _FULL
    -0.07
    @Column
    -0.07
    ">@
    -0.06
    @qq
    -0.06
    飗
    -0.06
    .non
    -0.06
    .#
    -0.06
    POSITIVE LOGITS
    ROPERTY
    0.07
    ichert
    0.07
    حكوم
    0.07
    文學
    0.07
     Hermione
    0.07
     bande
    0.07
    דות
    0.06
     Centro
    0.06
    .playlist
    0.06
     أكد
    0.06
    Act Density 0.074%

    No Known Activations