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

    Neuronpedia

    INDEX
    Explanations

    to/for

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Nigeria
    -0.06
    ，她
    -0.06
    _deck
    -0.06
    ispecies
    -0.06
    .MON
    -0.06
     огранич
    -0.06
    iliyor
    -0.06
    審
    -0.06
    noc
    -0.06
     Milton
    -0.06
    POSITIVE LOGITS
     고
    0.07
    Ni
    0.07
    ORIZ
    0.06
     keyst
    0.06
     }
↵
↵
↵
    0.06
     realtime
    0.06
     土
    0.06
     �
    0.06
     targets
    0.06
     STDOUT
    0.06
    Act Density 0.001%

    No Known Activations