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

    Neuronpedia

    INDEX
    Explanations

    of

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    UTTON
    -0.07
     Houses
    -0.07
    723
    -0.07
    permissions
    -0.07
    chia
    -0.07
    ーロ
    -0.06
     becoming
    -0.06
     preferably
    -0.06
    ്�
    -0.06
    Subsystem
    -0.06
    POSITIVE LOGITS
     $_
    0.06
     امید
    0.06
     Phil
    0.06
     Yahoo
    0.06
     Bart
    0.06
     unknow
    0.06
    .EMAIL
    0.06
     Ост
    0.06
     peru
    0.06
    ь
    0.06
    Act Density 0.002%

    No Known Activations