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

    Neuronpedia

    INDEX
    Explanations

    non-alphanumeric characters

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    usr
    -0.08
     instructor
    -0.07
     Clim
    -0.06
     dealloc
    -0.06
     notifications
    -0.06
    Cases
    -0.06
    .ViewModel
    -0.06
    engo
    -0.06
    compat
    -0.06
    akespeare
    -0.06
    POSITIVE LOGITS
     intersections
    0.07
     redundant
    0.06
    Previously
    0.06
     tạm
    0.06
    ِر
    0.06
    Bone
    0.06
    irit
    0.06
     cậu
    0.06
     콜
    0.06
     firewall
    0.06
    Act Density 0.025%

    No Known Activations