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

    Neuronpedia

    INDEX
    Explanations

    DOCTYPE

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     impactful
    -0.06
    _CID
    -0.06
    状况
    -0.06
    theorem
    -0.06
    _resume
    -0.06
     accelerator
    -0.06
     shocking
    -0.06
     nhu
    -0.06
    _HIGH
    -0.06
     Peel
    -0.06
    POSITIVE LOGITS
     breasts
    0.07
    /"↵↵
    0.06
    give
    0.06
    Lt
    0.06
     Sgt
    0.06
    career
    0.06
    ()*
    0.06
    ."},↵
    0.06
    dv
    0.06
     robbed
    0.06
    Act Density 0.001%

    No Known Activations