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

    Neuronpedia

    INDEX
    Explanations

    start of sentences

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Proz
    -0.08
     
    -0.08
    కు
    -0.08
     protests
    -0.08
    ్స
    -0.08
     Einen
    -0.07
    Href
    -0.07
     unang
    -0.07
    /set
    -0.07
     կամ
    -0.07
    POSITIVE LOGITS
     மேலும்
    0.09
    enable
    0.08
     물론
    0.08
     Thus
    0.08
     त्यामुळे
    0.07
    ivre
    0.07
     ಆದ
    0.07
     Furthermore
    0.07
     Vitt
    0.07
     gyro
    0.07
    Act Density 0.699%

    No Known Activations