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

    Neuronpedia

    INDEX
    Explanations

    adhere

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     平
    -0.07
    ------+------+
    -0.07
     jamais
    -0.07
    ickest
    -0.07
    功
    -0.07
     precio
    -0.07
     gleich
    -0.07
     �
    -0.07
     않는
    -0.06
     federally
    -0.06
    POSITIVE LOGITS
     adhere
    0.13
     adher
    0.10
    hi
    0.07
    .Here
    0.07
    hesive
    0.07
     LDL
    0.07
     demonstration
    0.06
    SION
    0.06
    HR
    0.06
     Jerome
    0.06
    Act Density 0.003%

    No Known Activations