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

    Neuronpedia

    INDEX
    Explanations

    Picking someone up

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     lm
    -0.07
     DataSet
    -0.07
    TLS
    -0.07
    /dc
    -0.06
     diag
    -0.06
    	My
    -0.06
    jal
    -0.06
     Di
    -0.06
     Rush
    -0.06
     snippets
    -0.06
    POSITIVE LOGITS
     příro
    0.07
    abr
    0.07
    πε
    0.06
    -ie
    0.06
    _altern
    0.06
     otev
    0.06
     зв
    0.06
    ......
    0.06
    plaintext
    0.06
    _relationship
    0.05
    Act Density 0.003%

    No Known Activations