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

    Neuronpedia

    INDEX
    Explanations

    technical writing

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ?s
    -0.06
    [block
    -0.06
     ALOG
    -0.06
     mitig
    -0.06
    )get
    -0.06
     násled
    -0.06
    Dirs
    -0.05
    偏
    -0.05
     helicopt
    -0.05
     enf
    -0.05
    POSITIVE LOGITS
     βο
    0.07
     vera
    0.07
    .N
    0.07
    осков
    0.06
    delivr
    0.06
     lover
    0.06
     '',
    0.06
    族
    0.06
    KC
    0.06
    alie
    0.06
    Act Density 0.472%

    No Known Activations