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

    Neuronpedia

    INDEX
    Explanations

    code symbols

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     wlan
    -0.07
    286
    -0.06
     이미
    -0.06
     chút
    -0.06
    667
    -0.06
    .ForEach
    -0.06
     krb
    -0.06
     silently
    -0.06
    Fl
    -0.06
    jspx
    -0.06
    POSITIVE LOGITS
    ี
    0.07
    ,"↵
    0.07
    (hex
    0.07
    เวลา
    0.06
    (ir
    0.06
     accord
    0.06
     _____
    0.06
     complaint
    0.06
    件事
    0.06
     �
    0.06
    Act Density 0.058%

    No Known Activations