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

    Neuronpedia

    INDEX
    Explanations

    Software licenses and modifications

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     deform
    -0.06
    rances
    -0.06
    _SCHED
    -0.06
    Mapper
    -0.06
    <span
    -0.06
    hee
    -0.06
    _device
    -0.06
    .related
    -0.06
     Hide
    -0.06
     zs
    -0.05
    POSITIVE LOGITS
     PL
    0.07
    tej
    0.07
    té
    0.07
    ::::::::
    0.06
     sunny
    0.06
     inaccessible
    0.06
     disguise
    0.06
     Terrain
    0.06
     сост
    0.06
     HALF
    0.06
    Act Density 0.007%

    No Known Activations