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

    Neuronpedia

    INDEX
    Explanations

    News/Q&A snippets

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     She
    -0.07
     Salesforce
    -0.06
     planets
    -0.06
     apt
    -0.06
     simples
    -0.06
    Safe
    -0.06
     Tal
    -0.06
     holder
    -0.06
     prospect
    -0.06
     proposing
    -0.06
    POSITIVE LOGITS
    peri
    0.07
     веч
    0.06
    vers
    0.06
     graffiti
    0.06
     authored
    0.06
    コン
    0.06
    .HTTP
    0.06
    бу
    0.06
    .deg
    0.06
    ezi
    0.06
    Act Density 0.097%

    No Known Activations