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

    Neuronpedia

    INDEX
    Explanations

    Legal documents

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .epsilon
    -0.07
    \u
    -0.07
     Keith
    -0.07
     subscriptions
    -0.07
     Keeps
    -0.07
     Siemens
    -0.07
     Donald
    -0.07
     Jensen
    -0.07
     undergoing
    -0.06
    Extensions
    -0.06
    POSITIVE LOGITS
    上班
    0.07
    팃
    0.07
     mention
    0.07
    APE
    0.07
    ⺠
    0.07
    柷
    0.06
     press
    0.06
    _trait
    0.06
     запис
    0.06
    ቢ
    0.06
    Act Density 0.007%

    No Known Activations