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

    Neuronpedia

    INDEX
    Explanations

    hyphen

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    éĽ¾
    -0.32
    Later
    -0.30
     Later
    -0.28
     infer
    -0.28
    ãĥªãĥ³ãĤ°
    -0.28
     fog
    -0.27
     later
    -0.27
    later
    -0.26
     afterward
    -0.25
    Works
    -0.25
    POSITIVE LOGITS
    ungs
    0.30
    iel
    0.28
    IEL
    0.27
     DISCLAIMED
    0.27
    åĬ©
    0.25
    ade
    0.25
    __/
    0.25
    è§ĦåĪĴ
    0.24
    gnore
    0.24
    avel
    0.24
    Act Density 0.006%

    No Known Activations