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

    Neuronpedia

    INDEX
    Explanations

    quotation mark

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     When
    -0.07
    When
    -0.07
     Wednesday
    -0.07
     �
    -0.06
     coherent
    -0.06
    Loading
    -0.06
     buffs
    -0.06
     accessible
    -0.06
     converted
    -0.06
     looping
    -0.06
    POSITIVE LOGITS
     secara
    0.07
    eckého
    0.07
    मक
    0.07
     fleeting
    0.07
    sold
    0.06
    lasyon
    0.06
    'class
    0.06
    okus
    0.06
     نماز
    0.06
    体育
    0.06
    Act Density 0.005%

    No Known Activations