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

    Neuronpedia

    INDEX
    Explanations

    include

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     sacrifice
    -0.07
    obj
    -0.06
     gdzie
    -0.06
     quelques
    -0.06
     Dě
    -0.06
     Another
    -0.06
     dod
    -0.06
    ((↵
    -0.06
     perfect
    -0.06
     comed
    -0.06
    POSITIVE LOGITS
     mView
    0.07
     zví
    0.06
    .ButterKnife
    0.06
     autogenerated
    0.06
     ancor
    0.06
     багат
    0.06
    day
    0.06
    numero
    0.06
    ्रत
    0.06
    	GLuint
    0.06
    Act Density 0.000%

    No Known Activations