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

    Neuronpedia

    INDEX
    Explanations

    Text improvement/creation

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    -0.07
    _Max
    -0.07
    緊
    -0.06
     spaced
    -0.06
    -0.06
     Vk
    -0.06
     metod
    -0.06
    .hr
    -0.06
    esus
    -0.06
    -0.06
    POSITIVE LOGITS
    исс
    0.07
     mobil
    0.06
     servi
    0.06
    .Generated
    0.06
     располож
    0.06
     address
    0.06
    DONE
    0.06
     librarian
    0.06
    	command
    0.06
     infant
    0.06
    Act Density 0.163%

    No Known Activations