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

    Neuronpedia

    INDEX
    Explanations

    2

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    第
    -0.07
    olph
    -0.07
    童
    -0.07
     الدين
    -0.07
    _pending
    -0.06
     špat
    -0.06
     tweaking
    -0.06
    λό
    -0.06
     сентября
    -0.06
    822
    -0.06
    POSITIVE LOGITS
     activist
    0.07
     `,
    0.07
     AL
    0.07
     AG
    0.06
     rez
    0.06
     specimens
    0.06
    AMI
    0.06
     capabilities
    0.06
     Ui
    0.06
     header
    0.06
    Act Density 0.039%

    No Known Activations