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

    Neuronpedia

    INDEX
    Explanations

    -

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Elm
    -0.07
    аксим
    -0.07
     Pang
    -0.06
     Hank
    -0.06
     Fant
    -0.06
     onLoad
    -0.06
    proper
    -0.06
     begging
    -0.06
     spoken
    -0.06
     attachments
    -0.06
    POSITIVE LOGITS
    яв
    0.08
    �
    0.07
    ์↵
    0.06
    งใน
    0.06
    _days
    0.06
     chce
    0.06
    upos
    0.06
    ...↵↵
    0.06
    Trump
    0.06
     vự
    0.06
    Act Density 0.001%

    No Known Activations