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

    Neuronpedia

    INDEX
    Explanations

    punctuation

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    nr
    -0.07
     @$_
    -0.06
    Xd
    -0.06
    ์จ
    -0.06
     Alone
    -0.06
     nj
    -0.06
    borg
    -0.06
    _firestore
    -0.06
     الله
    -0.06
    Infos
    -0.06
    POSITIVE LOGITS
     substant
    0.06
    (mail
    0.06
    brew
    0.06
     hollow
    0.06
     Psi
    0.06
    ��
    0.06
     marketplace
    0.06
     используется
    0.06
    (mb
    0.06
     배
    0.06
    Act Density 0.005%

    No Known Activations