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

    Neuronpedia

    INDEX
    Explanations

    maybe

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Neb
    -0.07
    .Push
    -0.06
     Note
    -0.06
     verde
    -0.06
     hybrids
    -0.06
    grades
    -0.06
    $(
    -0.06
     createAction
    -0.06
     enhances
    -0.06
     weakened
    -0.06
    POSITIVE LOGITS
     Tournament
    0.07
     Agricultural
    0.06
    -signed
    0.06
     );
↵
    0.06
    mental
    0.06
     nákup
    0.06
     obliv
    0.06
    야
    0.06
    олож
    0.06
     Tyson
    0.06
    Act Density 0.005%

    No Known Activations