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

    Neuronpedia

    INDEX
    Explanations

    end of phrases/sentences

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     distractions
    -0.08
     innovative
    -0.06
    ESS
    -0.06
    ess
    -0.06
    _metrics
    -0.06
    ounced
    -0.06
    �
    -0.06
     obedient
    -0.06
    ργ
    -0.06
     prompting
    -0.06
    POSITIVE LOGITS
     Reduced
    0.07
    remove
    0.07
     Odds
    0.06
    "[
    0.06
    .pref
    0.06
     MSNBC
    0.06
     usleep
    0.06
     ｰ
    0.06
     Gab
    0.06
    Spatial
    0.06
    Act Density 0.001%

    No Known Activations