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

    Neuronpedia

    INDEX
    Explanations

    the

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    startswith
    -0.08
     topic
    -0.08
    difference
    -0.07
    gressor
    -0.07
     Gdk
    -0.06
    Topic
    -0.06
    .offsetTop
    -0.06
     embeddings
    -0.06
    _bindings
    -0.06
     interaction
    -0.06
    POSITIVE LOGITS
    ????????
    0.07
    *);↵
    0.07
    Mut
    0.06
     chin
    0.06
    .mar
    0.06
     联
    0.06
     bouquet
    0.06
     sacrificing
    0.06
     observing
    0.06
    .alibaba
    0.06
    Act Density 0.090%

    No Known Activations