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

    Neuronpedia

    INDEX
    Explanations

    PCR primers

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     pledge
    -0.07
    poke
    -0.07
     superintendent
    -0.07
    Ap
    -0.07
     module
    -0.06
     Pizza
    -0.06
    onnen
    -0.06
     stud
    -0.06
     ceramic
    -0.06
     rightly
    -0.06
    POSITIVE LOGITS
    usually
    0.07
     Supern
    0.06
    ><!--
    0.06
     смерти
    0.06
    .transfer
    0.06
    ัวร
    0.06
    .Unlock
    0.06
     생각
    0.06
     تعریف
    0.06
    ческой
    0.06
    Act Density 0.007%

    No Known Activations