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

    Neuronpedia

    INDEX
    Explanations

    now

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     florida
    -0.07
     Cara
    -0.07
     หร
    -0.07
     степ
    -0.06
    층의
    -0.06
    َة
    -0.06
    .".
    -0.06
    …"
    -0.06
    ']."
    -0.06
    -commit
    -0.06
    POSITIVE LOGITS
     matrimon
    0.06
    志
    0.06
    .AddListener
    0.06
     accession
    0.06
     subnet
    0.06
    nant
    0.06
    _CNT
    0.06
     soğ
    0.06
    imd
    0.06
    與
    0.06
    Act Density 0.001%

    No Known Activations