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

    Neuronpedia

    INDEX
    Explanations

    say

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ائع
    -0.07
    .ylabel
    -0.07
     linen
    -0.07
    _perf
    -0.06
     lunch
    -0.06
    .DeserializeObject
    -0.06
    卫生
    -0.06
    “These
    -0.06
    _mappings
    -0.06
     �
    -0.06
    POSITIVE LOGITS
     say
    0.08
    /thumb
    0.07
     tall
    0.07
    �
    0.07
     click
    0.06
     unittest
    0.06
     FG
    0.06
     saying
    0.06
    neh
    0.06
     Strait
    0.06
    Act Density 0.037%

    No Known Activations