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

    Neuronpedia

    INDEX
    Explanations

    MMM

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Ar
    -0.08
     separ
    -0.07
    Cert
    -0.07
     arom
    -0.06
     breed
    -0.06
    clud
    -0.06
    fort
    -0.06
    landscape
    -0.06
     PROP
    -0.06
     Retrie
    -0.06
    POSITIVE LOGITS
    ▋▋
    0.07
    ितन
    0.07
    ByPrimaryKey
    0.07
    ,
↵
↵
    0.06
    '}↵↵
    0.06
    і
    0.06
    .ErrorMessage
    0.06
    лено
    0.06
     стоит
    0.06
    üncü
    0.06
    Act Density 0.004%

    No Known Activations