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

    Neuronpedia

    INDEX
    Explanations

    explaining specific code

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Fin
    0.39
     ധ
    0.39
    <em>
    0.39
     MFA
    0.38
     curvature
    0.37
     Astro
    0.37
     OK
    0.36
     FAS
    0.36
     DM
    0.36
     Evans
    0.35
    POSITIVE LOGITS
     Sabemos
    0.45
     OP
    0.44
    OP
    0.42
    мпания
    0.41
    bumptech
    0.41
    Even
    0.40
     hello
    0.40
    hello
    0.40
    ​​​​
    0.40
    源代码
    0.40
    Act Density 0.000%

    No Known Activations