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

    Neuronpedia

    INDEX
    Explanations

    shebang lines and interpreters

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     gland
    0.43
     मल्टीप्लिकेशन
    0.39
     glands
    0.38
     sulphuric
    0.38
     pyrr
    0.38
    뢨
    0.37
     fondant
    0.37
    subkey
    0.36
    lockSeconds
    0.36
     responseObject
    0.36
    POSITIVE LOGITS
    #!/
    1.23
    #!
    0.85
    She
    0.77
    interpreter
    0.75
     She
    0.74
     interpreter
    0.74
     "#
    0.67
     interpreters
    0.66
     Interpreter
    0.66
    Interpreter
    0.64
    Act Density 0.044%

    No Known Activations