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

    Neuronpedia

    INDEX
    Explanations

    memories

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     royal
    -0.08
    -request
    -0.07
     dealer
    -0.07
     ambition
    -0.06
    expression
    -0.06
    year
    -0.06
     Müller
    -0.06
    είς
    -0.06
    igmatic
    -0.06
    430
    -0.06
    POSITIVE LOGITS
    _intf
    0.07
    �
    0.06
    ::::::::
    0.06
     tranny
    0.06
    itä
    0.06
     jLabel
    0.06
    obox
    0.06
     розта
    0.06
    PING
    0.06
     automation
    0.06
    Act Density 0.156%

    No Known Activations