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

    Neuronpedia

    INDEX
    Explanations

    ^

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    агато
    -0.07
    เต
    -0.06
    Detach
    -0.06
     affid
    -0.06
     riders
    -0.06
    _alpha
    -0.06
    riv
    -0.06
    embros
    -0.06
     scalable
    -0.06
     zh
    -0.06
    POSITIVE LOGITS
     추가
    0.07
    웠
    0.06
    	mesh
    0.06
    zia
    0.06
     Resize
    0.06
    dated
    0.06
     attraction
    0.06
    _PERMISSION
    0.06
    (agent
    0.06
    decrypt
    0.06
    Act Density 0.000%

    No Known Activations