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

    Neuronpedia

    INDEX
    Explanations

    Year in citations

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     mask
    -0.07
     bother
    -0.07
     Mask
    -0.07
    yeah
    -0.06
     administered
    -0.06
    Holder
    -0.06
     Ghost
    -0.06
     Samp
    -0.06
    .metamodel
    -0.06
    rafted
    -0.06
    POSITIVE LOGITS
    \Dependency
    0.08
    200
    0.06
    201
    0.06
     obliv
    0.06
    buttonShape
    0.06
    .xtext
    0.06
     určitě
    0.06
    /story
    0.06
     jewish
    0.06
    골
    0.06
    Act Density 0.016%

    No Known Activations