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

    Neuronpedia

    INDEX
    Explanations

    past tense auxiliary verbs

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Sidney
    -0.07
     stupidity
    -0.06
     Beispiel
    -0.06
     boobs
    -0.06
     Lynn
    -0.06
     Trinidad
    -0.06
    �
    -0.06
     FEMA
    -0.06
     Τ
    -0.05
     webpage
    -0.05
    POSITIVE LOGITS
    *C
    0.08
    touches
    0.07
    Deep
    0.07
    inburgh
    0.07
    jing
    0.07
     нему
    0.06
    _EM
    0.06
     پیام
    0.06
     Amber
    0.06
    ิป
    0.06
    Act Density 0.057%

    No Known Activations