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

    Neuronpedia

    INDEX
    Explanations

    Future tense and negation

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    -handle
    -0.08
    camel
    -0.07
    Anchor
    -0.07
    ssql
    -0.07
    تان
    -0.06
     Anchor
    -0.06
    parm
    -0.06
    handler
    -0.06
     ви
    -0.06
    pyx
    -0.06
    POSITIVE LOGITS
     Pres
    0.07
    หนด
    0.06
     повед
    0.06
    ンディ
    0.06
     coloc
    0.06
     completed
    0.06
     announces
    0.06
     июля
    0.06
     Boss
    0.06
     medically
    0.06
    Act Density 0.118%

    No Known Activations