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

    Neuronpedia

    INDEX
    Explanations

    if

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    สร
    -0.08
    ると
    -0.07
     Performing
    -0.07
    ique
    -0.07
    меш
    -0.07
     список
    -0.07
    اویر
    -0.07
    ンブ
    -0.07
    ryptography
    -0.06
     про
    -0.06
    POSITIVE LOGITS
    :boolean
    0.07
     scans
    0.07
    Purple
    0.06
    056
    0.06
     Trie
    0.06
    />.
    0.06
    mw
    0.06
     pit
    0.06
    .style
    0.06
    reme
    0.06
    Act Density 0.010%

    No Known Activations