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

    Neuronpedia

    INDEX
    Explanations

    in

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    DAQ
    -0.07
    _MATERIAL
    -0.07
     intervening
    -0.07
    ické
    -0.06
     Assembly
    -0.06
    acceptable
    -0.06
    hood
    -0.06
     international
    -0.06
    (xs
    -0.06
    führ
    -0.06
    POSITIVE LOGITS
    RefPtr
    0.06
     ries
    0.06
    <Props
    0.06
     CRM
    0.06
     처음
    0.06
     Symptoms
    0.06
    _send
    0.06
    .</
    0.06
     ',
    0.06
     agricult
    0.06
    Act Density 0.367%

    No Known Activations