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

    Neuronpedia

    INDEX
    Explanations

    Inheritance

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    iek
    -0.06
    VIDIA
    -0.06
    FIN
    -0.06
    	rows
    -0.06
    opian
    -0.06
    вала
    -0.06
    .signup
    -0.06
    .sections
    -0.06
     quelle
    -0.06
    _minus
    -0.05
    POSITIVE LOGITS
    ETwitter
    0.07
    โน
    0.07
     Dos
    0.07
     mosquitoes
    0.06
    MemoryWarning
    0.06
     immensely
    0.06
    ﻤ
    0.06
    hud
    0.06
     qq
    0.06
     muy
    0.06
    Act Density 0.003%

    No Known Activations