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

    Neuronpedia

    INDEX
    Explanations

    discussions

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     mobile
    -0.07
     stairs
    -0.07
     watch
    -0.07
    _blocking
    -0.07
     CLASS
    -0.06
    bench
    -0.06
     fixed
    -0.06
     behavior
    -0.06
     téc
    -0.06
     tickets
    -0.06
    POSITIVE LOGITS
     RuntimeError
    0.06
     softened
    0.06
     ruining
    0.06
     Obtain
    0.06
    _aut
    0.06
    でしょう
    0.06
    ">'.
    0.06
    .current
    0.06
    	append
    0.06
    HttpResponse
    0.06
    Act Density 0.081%

    No Known Activations