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

    Neuronpedia

    INDEX
    Explanations

    Shell

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    287
    -0.07
    189
    -0.07
    285
    -0.07
    ()=>{↵
    -0.07
    297
    -0.07
    29
    -0.07
     contrast
    -0.07
    rd
    -0.06
    .`|`↵
    -0.06
     Monument
    -0.06
    POSITIVE LOGITS
     shell
    0.14
     shells
    0.14
     Shell
    0.13
    Shell
    0.12
    shell
    0.11
     Michelle
    0.09
    -shell
    0.09
    Michelle
    0.09
     Hull
    0.08
    ell
    0.08
    Act Density 0.007%

    No Known Activations