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

    Neuronpedia

    INDEX
    Explanations

    Bach

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    spec
    -0.25
    lij
    -0.25
    bj
    -0.25
    åħ¹
    -0.24
    аÑĢаÑĤ
    -0.24
     spec
    -0.24
    _spec
    -0.24
     lạ
    -0.24
    à¹Ħล
    -0.24
    å¶Ļ
    -0.23
    POSITIVE LOGITS
     Romance
    0.28
    -packages
    0.27
    Simply
    0.27
     Pony
    0.27
     squirt
    0.26
     Homeland
    0.26
    èijµ
    0.26
     Near
    0.25
    æľįåĬ¡èĥ½åĬĽ
    0.25
     capacity
    0.25
    Act Density 0.008%

    No Known Activations