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

    Neuronpedia

    INDEX
    Explanations

    code and configuration

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _live
    -0.07
    face
    -0.07
     heals
    -0.07
    -linux
    -0.06
     delivers
    -0.06
     contr
    -0.06
     upstairs
    -0.06
     molecules
    -0.06
    .access
    -0.06
     specify
    -0.06
    POSITIVE LOGITS
    succ
    0.06
    .named
    0.06
     GROUP
    0.06
     monarch
    0.06
     parach
    0.06
    chers
    0.06
    ��
    0.06
    \Data
    0.06
    ection
    0.06
     vandal
    0.06
    Act Density 0.285%

    No Known Activations