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

    Neuronpedia

    INDEX
    Explanations

    costs

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    draulic
    -0.07
    ματος
    -0.07
    _es
    -0.07
    .codes
    -0.06
     препара
    -0.06
     dimensional
    -0.06
     بسی
    -0.06
    ']!='
    -0.06
     наруж
    -0.06
     ум
    -0.06
    POSITIVE LOGITS
     ruining
    0.07
    may
    0.07
    (tree
    0.06
    bringing
    0.06
     bred
    0.06
     damn
    0.06
     capt
    0.06
    apply
    0.06
     MLA
    0.06
    intendent
    0.06
    Act Density 0.017%

    No Known Activations