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

    Neuronpedia

    INDEX
    Explanations

    Audio specifications

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    /Object
    -0.08
     coherence
    -0.08
     eens
    -0.07
     isn
    -0.07
     isn't
    -0.07
     angla
    -0.07
     англий
    -0.07
     الإنجليزية
    -0.07
     metropolis
    -0.07
    -0.07
    POSITIVE LOGITS
    ლების
    0.08
     hm
    0.08
    Ig
    0.08
    conduct
    0.08
     claim
    0.08
     cuadrados
    0.08
    ▫
    0.08
    _multiple
    0.08
     rohkem
    0.08
     lí
    0.08
    Act Density 0.005%
    No Known Activations