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

    Neuronpedia

    INDEX
    Explanations

    prompt

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Im
    -0.07
     Technique
    -0.07
    专家学者
    -0.07
    협
    -0.07
     neighbor
    -0.06
     parenting
    -0.06
     노
    -0.06
     casually
    -0.06
    Scientists
    -0.06
     doubts
    -0.06
    POSITIVE LOGITS
    ⌕
    0.07
    .CreateDirectory
    0.07
    _DECREF
    0.07
    /lic
    0.07
    _normal
    0.07
    🎠
    0.06
    opl
    0.06
     jumped
    0.06
    .Sdk
    0.06
    מערכ
    0.06
    Act Density 0.025%

    No Known Activations