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

    Neuronpedia

    INDEX
    Explanations

    Submarines and naval warfare

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    仰
    -0.07
    _tokenize
    -0.07
    INAL
    -0.07
     sunny
    -0.06
    ائم
    -0.06
    ाओ
    -0.06
    stars
    -0.06
    术
    -0.06
     серпня
    -0.06
     aba
    -0.06
    POSITIVE LOGITS
     decide
    0.08
    (reply
    0.07
    ={{↵
    0.07
     armored
    0.07
     disciples
    0.07
    .sorted
    0.06
    labilir
    0.06
    _InitStruct
    0.06
     calculates
    0.06
    _bridge
    0.06
    Act Density 0.011%

    No Known Activations