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
    열
    -0.08
    mitted
    -0.06
     strán
    -0.06
    VL
    -0.06
     όπου
    -0.06
    中文
    -0.06
    زام
    -0.06
    िच
    -0.06
    igmatic
    -0.06
    rium
    -0.06
    POSITIVE LOGITS
    艾
    0.07
     Throwable
    0.07
     tsl
    0.06
     socio
    0.06
     assail
    0.06
     america
    0.06
    =''):↵
    0.06
     airports
    0.06
     dictionaries
    0.06
     scho
    0.06
    Act Density 0.005%

    No Known Activations