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
     �
    -0.07
     Defendants
    -0.07
     OPTIONAL
    -0.06
     means
    -0.06
    층의
    -0.06
     Invent
    -0.06
    ledo
    -0.06
    ักส
    -0.06
     З
    -0.06
     reconsider
    -0.06
    POSITIVE LOGITS
    /
    0.09
    /how
    0.07
     estoy
    0.06
     /
    0.06
    /connect
    0.06
    weise
    0.06
    ton
    0.06
    ytt
    0.06
    ("/{
    0.06
     若要
    0.06
    Act Density 0.040%

    No Known Activations