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
    vature
    -0.08
    .Face
    -0.07
     Execution
    -0.07
    陟
    -0.07
    ật
    -0.06
    _FW
    -0.06
    ases
    -0.06
    STITUTE
    -0.06
    滥用
    -0.06
     şu
    -0.06
    POSITIVE LOGITS
    ={()=>
    0.07
    oron
    0.07
     Wichita
    0.07
    ﮀ
    0.07
     Morton
    0.07
    роб
    0.06
     morale
    0.06
    Portland
    0.06
    在那里
    0.06
     הקשור
    0.06
    Act Density 0.000%

    No Known Activations