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

    Neuronpedia

    INDEX
    Explanations

    Chatbot prompts and responses

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     preciosa
    -0.09
     PTO
    -0.08
     Hawkins
    -0.08
     Siy
    -0.08
     poth
    -0.08
     அனைவர
    -0.08
     Azul
    -0.07
     метро
    -0.07
     vp
    -0.07
     Quantum
    -0.07
    POSITIVE LOGITS
     rhetoric
    0.10
     bevatten
    0.10
     contain
    0.10
     выраз
    0.09
    表达
    0.09
    力度
    0.09
    Contain
    0.09
     rhetorical
    0.09
     tone
    0.09
     propaganda
    0.09
    Act Density 0.080%

    No Known Activations