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

    Neuronpedia

    INDEX
    Explanations

    full

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Lions
    -0.07
    _iface
    -0.06
     armed
    -0.06
    彼女
    -0.06
    艾
    -0.06
     Lod
    -0.06
    ATTER
    -0.06
     Buf
    -0.06
     POW
    -0.06
    敌
    -0.06
    POSITIVE LOGITS
     brainstorm
    0.08
    _author
    0.07
    `(
    0.06
    �
    0.06
    (success
    0.06
     ParseException
    0.06
    ��
    0.06
    .replaceAll
    0.06
    -pr
    0.06
    	slot
    0.06
    Act Density 0.010%

    No Known Activations