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

    Neuronpedia

    INDEX
    Explanations

    201

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     writeFile
    -0.07
    .dex
    -0.06
     hb
    -0.06
     hills
    -0.06
     puck
    -0.06
    ':''
    -0.06
     abandon
    -0.06
     jazy
    -0.06
     io
    -0.06
     quanh
    -0.06
    POSITIVE LOGITS
    201
    0.08
     وش
    0.07
    .SM
    0.07
    Ont
    0.07
    Đ
    0.06
    Premium
    0.06
     �
    0.06
    191
    0.06
    987
    0.06
     predic
    0.06
    Act Density 0.007%

    No Known Activations