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

    Neuronpedia

    INDEX
    Explanations

    quotes

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Fk
    -0.08
     verder
    -0.07
     Wer
    -0.07
    -containing
    -0.07
     buenos
    -0.07
    -good
    -0.07
    Hmm
    -0.07
     refer
    -0.07
     Verder
    -0.07
     distracted
    -0.07
    POSITIVE LOGITS
     testament
    0.11
     homage
    0.11
    ，也是
    0.10
     acknowledgment
    0.10
     acknowledging
    0.10
    Acknowled
    0.10
     Einladung
    0.10
     acknowledgement
    0.09
     plea
    0.09
     convite
    0.09
    Act Density 0.086%

    No Known Activations