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

    Neuronpedia

    INDEX
    Explanations

    limitations and comparisons

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Manifest
    -0.07
    RESP
    -0.07
    requencies
    -0.07
     сни
    -0.06
    .mo
    -0.06
     е
    -0.06
    Include
    -0.06
     mitig
    -0.06
     meio
    -0.06
    ontology
    -0.06
    POSITIVE LOGITS
     联
    0.07
    _PROP
    0.07
     Zeit
    0.06
    (long
    0.06
    .Lerp
    0.06
     outfield
    0.06
     clear
    0.06
    に関
    0.06
     ending
    0.06
     能
    0.06
    Act Density 0.045%

    No Known Activations