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

    Neuronpedia

    INDEX
    Explanations

    through

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    'ex
    -0.07
     with
    -0.07
    fuck
    -0.06
     calling
    -0.06
    อท
    -0.06
    fraction
    -0.06
    [z
    -0.06
    registers
    -0.06
    ."','".$
    -0.06
    冷
    -0.06
    POSITIVE LOGITS
    enticate
    0.08
    .payment
    0.07
     technologies
    0.07
    益
    0.07
    .vaadin
    0.07
     Washington
    0.07
     Redis
    0.07
     prevention
    0.07
     Messiah
    0.06
    ः
    0.06
    Act Density 0.025%

    No Known Activations