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

    Neuronpedia

    INDEX
    Explanations

    random text excerpts

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    oader
    -0.31
    croft
    -0.28
    ä¸Ģ个èģĮä¸ļ
    -0.27
    åıijçĹħ
    -0.26
     prosper
    -0.26
    ë³ijìĽIJ
    -0.26
     prive
    -0.26
    cles
    -0.25
    éĤ£æł·çļĦ
    -0.25
    леÑĩ
    -0.24
    POSITIVE LOGITS
    ifers
    0.26
     circuit
    0.25
     velocity
    0.25
    è½»
    0.25
    vert
    0.25
    PasswordEncoder
    0.24
    axy
    0.23
    éĴŁ
    0.23
     hold
    0.23
    grade
    0.23
    Act Density 0.001%

    No Known Activations