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

    Neuronpedia

    INDEX
    Explanations

    slashes and semicolons

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     handler
    -0.08
     pollution
    -0.07
    Manager
    -0.07
    fol
    -0.07
     Handlers
    -0.07
     cases
    -0.07
    _program
    -0.07
     execution
    -0.06
     plainly
    -0.06
     websites
    -0.06
    POSITIVE LOGITS
    Bài
    0.07
    .setSelected
    0.07
     ELF
    0.07
    [];
↵
    0.06
    ;text
    0.06
    abal
    0.06
    .visitVarInsn
    0.06
    ,buf
    0.06
    [res
    0.06
    (Auth
    0.06
    Act Density 0.001%

    No Known Activations