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

    Neuronpedia

    INDEX
    Explanations

    to

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    特色
    -0.07
    _Method
    -0.07
     lowers
    -0.07
    PathParam
    -0.06
     kindergarten
    -0.06
     Solve
    -0.06
    hasOne
    -0.06
     iar
    -0.06
     Ell
    -0.06
     mkdir
    -0.06
    POSITIVE LOGITS
    νοντας
    0.06
    _"
    0.06
     rebuild
    0.06
    えて
    0.06
    ients
    0.06
     게시
    0.06
    _CAM
    0.05
    ices
    0.05
     Removal
    0.05
    Buffers
    0.05
    Act Density 0.078%

    No Known Activations