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

    Neuronpedia

    INDEX
    Explanations

    ]

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     okay
    -0.07
    .nih
    -0.07
     measurable
    -0.07
     einige
    -0.07
    _ct
    -0.07
    plode
    -0.07
     ok
    -0.07
    etype
    -0.06
    Prot
    -0.06
    .car
    -0.06
    POSITIVE LOGITS
    (Login
    0.06
    (TABLE
    0.06
                            
↵
    0.06
    (inputStream
    0.06
     لذا
    0.06
    iciency
    0.06
    鐘
    0.06
     shards
    0.06
    //
↵
    0.06
    ，她
    0.05
    Act Density 0.003%

    No Known Activations