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

    Neuronpedia

    INDEX
    Explanations

    I

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     hopefully
    -0.07
     spar
    -0.07
    当今
    -0.07
     mast
    -0.07
    两天
    -0.07
    รว
    -0.06
    必须
    -0.06
     inst
    -0.06
     constraints
    -0.06
     �
    -0.06
    POSITIVE LOGITS
     Perfect
    0.08
     Rename
    0.07
     ş
    0.07
    /pay
    0.07
     =='
    0.07
     yahoo
    0.07
    eness
    0.07
    =='
    0.07
     dünyanın
    0.07
    䐃
    0.06
    Act Density 0.040%

    No Known Activations