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

    Neuronpedia

    INDEX
    Explanations

    shell

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Better
    -0.07
    Save
    -0.07
     granddaughter
    -0.07
     safer
    -0.06
     Fragment
    -0.06
     diminished
    -0.06
    Dark
    -0.06
     expres
    -0.06
     riot
    -0.06
     Dark
    -0.06
    POSITIVE LOGITS
     shell
    0.10
    Shell
    0.09
     Shell
    0.09
     shells
    0.08
     용
    0.08
    сыл
    0.07
     Bone
    0.07
    shell
    0.07
    руб
    0.07
     Morg
    0.07
    Act Density 0.007%

    No Known Activations