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

    Neuronpedia

    INDEX
    Explanations

    states

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     &[
    -0.07
     займ
    -0.07
    డి
    -0.07
     ontvangt
    -0.07
     preocup
    -0.07
    OTP
    -0.07
    aveled
    -0.07
    freie
    -0.07
     danes
    -0.07
    .UTC
    -0.07
    POSITIVE LOGITS
     mentions
    0.12
    Mention
    0.12
     Mention
    0.11
     mention
    0.11
     mentioning
    0.10
     उल्लेख
    0.10
     erwähnt
    0.10
     hinted
    0.10
    mention
    0.10
     mentioned
    0.09
    Act Density 0.058%

    No Known Activations