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

    Neuronpedia

    INDEX
    Explanations

    114

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     webpage
    -0.07
     Stap
    -0.07
     mj
    -0.07
     بما
    -0.07
     CWE
    -0.06
     columns
    -0.06
     �
    -0.06
     objs
    -0.06
     Station
    -0.06
     Joined
    -0.06
    POSITIVE LOGITS
    113
    0.08
    114
    0.07
     Del
    0.07
     barr
    0.07
    ctions
    0.06
    112
    0.06
    Buf
    0.06
    каз
    0.06
    稿
    0.06
     dilation
    0.06
    Act Density 0.008%

    No Known Activations