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

    Neuronpedia

    INDEX
    Explanations

    eclipse

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Assets
    -0.07
    SignIn
    -0.07
     Justin
    -0.07
     Serena
    -0.07
     Lenin
    -0.06
     SER
    -0.06
     jejím
    -0.06
     juicy
    -0.06
    .NoSuch
    -0.06
     crumbs
    -0.06
    POSITIVE LOGITS
     eclipse
    0.08
     відпов
    0.07
    uzione
    0.07
    νη
    0.07
     xmlns
    0.07
    Validation
    0.07
     enclave
    0.07
    .eclipse
    0.07
     alignment
    0.06
    olist
    0.06
    Act Density 0.003%

    No Known Activations