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

    Neuronpedia

    INDEX
    Explanations

    le

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Arena
    -0.07
    -target
    -0.07
    """.
    -0.07
     bacon
    -0.06
    umbotron
    -0.06
     arrest
    -0.06
     Asp
    -0.06
    йте
    -0.06
    ','%
    -0.06
     bfd
    -0.06
    POSITIVE LOGITS
     perish
    0.07
     IEEE
    0.07
     concerted
    0.06
     आध
    0.06
    笔
    0.06
     मह
    0.06
    िच
    0.06
    ility
    0.06
    .Append
    0.06
    .setToolTip
    0.06
    Act Density 0.003%

    No Known Activations